Machine Learning
Robustness, Cost, and Attack-Surface Concentration in Phishing Detection
Julian Allagan, Mohamed Elbakary, Zohreh Safari et al. (+4 more)
Phishing detectors built on engineered website features attain near-perfect accuracy under i.i.d.\ evaluation, yet deployment security depends on robustness to post-deployment feature manipulation. We study this gap through a cost-aware evasion framework that models discrete, monotone feature edits under explicit attacker budgets. Three diagnostics are introduced: minimal evasion cost (MEC), the evasion survival rate $S(B)$, and the robustness concentration index (RCI). On the UCI Phishing Websites
benchmark (11\,055 instances, 30 ternary features), Logistic Regression, Random Forests, Gradient Boosted Trees, and XGBoost all achieve $\mathrm{AUC}\ge 0.979$ under static evaluation. Under budgeted sanitization-style evasion, robustness converges across architectures: the median MEC equals 2 with full features, and over 80% of successful minimal-cost evasions concentrate on three low-cost surface features. Feature restriction improves robustness only when it removes all dominant low-cost transitions. Under strict cost schedules, infrastructure-leaning feature sets exhibit 17-19% infeasible mass for ensemble models, while the median MEC among evadable instances remains unchanged. We formalize this convergence: if a positive fraction of correctly detected phishing instances admit evasion through a single feature transition of minimal cost $c_{\min}$, no classifier can raise the corresponding MEC
quantile above $c_{\min}$ without modifying the feature representation or cost model.
Adversarial robustness in phishing detection is governed by feature economics rather than model complexity.
Read the full abstract ▾
All authors Julian Allagan, Mohamed Elbakary, Zohreh Safari, Weizheng Gao, Gabrielle Morgan, Essence Morgan, Vladimir Deriglazov
Machine Learning · Cross-listed from stat.ML
Extending SSMs with the Exponentially Weighted Signature
Alexandre Bloch, Benjamin Walker, Joël Mouterde et al. (+3 more)
We introduce the exponentially weighted signature (EWS), a continuous-time model that computes iterated integrals of a path, where each increment is weighted by the
matrix exponential of a learnable generator over elapsed clock time. We prove that it solves a linear controlled differential equation, keeps the group-like structure and the universality of the signature, and satisfies a modified Chen identity, enabling a parallel scan. At depth one the EWS is a state-space model (SSM), and we map linear time-invariant SSMs, Mamba channels and Mamba-$2$ heads to it in closed form. The EWS extends SSMs through an arbitrary
matrix generator, a clock that generalises the step size to causal functionals of the input, and higher truncation depths that are non-linear in the path within a single layer. Empirically, the EWS achieves the highest average accuracy and rank on six long time-series classification
datasets, where depth generally helps. Learned clocks prove necessary for state tracking on formal
language tasks, and at depth one, the EWS matches or exceeds competing SSMs on regression and
forecasting with far fewer parameters.
Read the full abstract ▾
All authors Alexandre Bloch, Benjamin Walker, Joël Mouterde, Sam Morley, Samuel N. Cohen, Terry Lyons
Machine Learning
Improving RCT-Based Treatment Effect Estimation Under Covariate Mismatch via Calibrated Alignment
Amir Asiaee and Samhita Pal
Randomized controlled trials (RCTs) are the gold standard for estimating treatment effects, yet they are often underpowered for detecting effect heterogeneity. Large observational studies (OS) can supplement RCTs for conditional average treatment effect (CATE) estimation, but a key barrier is
covariate mismatch: the two sources measure different, only partially overlapping,
covariates. We propose CALM (Calibrated
ALignment under
covariate Mismatch), which learns
embeddings that map each source's features into a common representation space. OS outcome models are transferred to the RCT
embedding space and calibrated using trial data, preserving causal identification from randomization. Finite-sample risk bounds decompose into
alignment error, outcome-model complexity, and calibration complexity terms, making explicit when the learned
embedding is accurate enough to reduce variance. We instantiate CALM in two forms: a closed-form linear version, CALM-Lin, and a neural representation-learning version, CALM-NN. Across 51 simulation settings, calibration-based linear methods are effectively tied in linear-CATE regimes, while CALM-NN wins all 22 nonlinear-CATE settings by wide margins. Moreover, on two real-data studies CALM-NN delivers the largest gains over the trial-only baseline.
Read the full abstract ▾
Machine Learning
MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular data
Masoumeh Shafieinejad, Xi He, Mahshid Alinoori et al. (+6 more)
Synthetic data is often perceived as a silver-bullet solution to data anonymization and
privacy-preserving data publishing. Drawn from generative models like
diffusion models, synthetic data is expected to preserve the statistical properties of the original
dataset while remaining resilient to
privacy attacks. Recent developments of
diffusion models have been effective on a wide range of data types, but their
privacy resilience, particularly for tabular formats, remains largely unexplored. MIDST challenge sought a quantitative evaluation of the
privacy gain of synthetic tabular data generated by
diffusion models, with a specific focus on its resistance to membership inference attacks (MIAs). Given the heterogeneity and complexity of tabular data, multiple target models were explored for MIAs, including
diffusion models for single tables of mixed data types and multi-relational tables with interconnected constraints. MIDST inspired the development of novel black-box and white-box MIAs tailored to these target
diffusion models as a key outcome, enabling a comprehensive evaluation of their
privacy efficacy. The MIDST GitHub repository is available at https://github.com/VectorInstitute/MIDST
Read the full abstract ▾
All authors Masoumeh Shafieinejad, Xi He, Mahshid Alinoori, John Jewell, Sana Ayromlou, Wei Pang, Veronica Chatrath, Gauri Sharma, Deval Pandya
Machine Learning
SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits
Edward Lin, Sahil Modi, Siva Kumar Sastry Hari et al. (+30 more)
As agentic AI systems become increasingly capable of generating and optimizing GPU kernels, progress is constrained by
benchmarks that reward speedup over software baselines rather than proximity to hardware-efficient execution. We present SOL-ExecBench, a
benchmark of 235 CUDA kernel optimization problems extracted from 124 production and emerging AI models spanning
language,
diffusion,
vision, audio,
video, and hybrid architectures, targeting NVIDIA Blackwell GPUs. The
benchmark covers forward and backward workloads across BF16, FP8, and NVFP4, including kernels whose best performance is expected to rely on Blackwell-specific capabilities. Unlike prior
benchmarks that evaluate kernels primarily relative to software implementations, SOL-ExecBench measures performance against analytically derived Speed-of-Light (SOL) bounds computed by
SOLAR, our pipeline for deriving hardware-grounded SOL bounds, yielding a fixed target for hardware-efficient optimization. We report a SOL Score that quantifies how much of the gap between a release-defined scoring baseline and the hardware SOL bound a candidate kernel closes. To support robust evaluation of agentic optimizers, we additionally provide a sandboxed harness with GPU clock locking, L2 cache clearing, isolated subprocess execution, and static analysis based checks against common reward-hacking strategies. SOL-ExecBench reframes GPU kernel benchmarking from beating a mutable software baseline to closing the remaining gap to hardware Speed-of-Light.
Read the full abstract ▾
All authors Edward Lin, Sahil Modi, Siva Kumar Sastry Hari, Qijing Huang, Zhifan Ye, Nestor Qin, Fengzhe Zhou, Yuan Zhang, Jingquan Wang, Sana Damani, Dheeraj Peri, Ouye Xie, Aditya Kane, Moshe Maor, Michael Behar, Triston Cao, Rishabh Mehta, Vartika Singh, Vikram Sharma Mailthody, Terry Chen, Zihao Ye, Hanfeng Chen, Tianqi Chen, Vinod Grover, Wei Chen, Wei Liu, Eric Chung, Luis Ceze, Roger Bringmann, Cyril Zeller, Michael Lightstone, Christos Kozyrakis, Humphrey Shi
Machine Learning
DyMoE: Dynamic Expert Orchestration with Mixed-Precision Quantization for Efficient MoE Inference on Edge
Yuegui Huang, Zhiyuan Fang, Weiqi Luo et al. (+3 more)
Despite the computational efficiency of MoE models, the excessive
memory footprint and I/O overhead inherent in multi-expert architectures pose formidable challenges for real-time inference on resource-constrained edge platforms. While existing static methods struggle with a rigid latency-accuracy trade-off, we observe that expert importance is highly skewed and depth-dependent. Motivated by these insights, we propose DyMoE, a dynamic mixed-precision quantization framework designed for high-performance edge inference. Leveraging insights into expert importance skewness and depth-dependent sensitivity, DyMoE introduces: (1) importance-aware prioritization to dynamically quantize experts at runtime; (2) depth-adaptive scheduling to preserve semantic integrity in critical layers; and (3) look-ahead prefetching to overlap I/O stalls. Experimental results on commercial edge hardware show that DyMoE reduces Time-to-First-
Token (TTFT) by 3.44x-22.7x and up to a 14.58x speedup in Time-Per-Output-
Token (TPOT) compared to state-of-the-art offloading baselines, enabling real-time, accuracy-preserving MoE inference on resource-constrained edge devices.
Read the full abstract ▾
All authors Yuegui Huang, Zhiyuan Fang, Weiqi Luo, Ruoyu Wu, Wuhui Chen, Zibin Zheng
Machine Learning · Cross-listed from cs.RO
Meanings and Measurements: Multi-Agent Probabilistic Grounding for Vision-Language Navigation
Swagat Padhan, Lakshya Jain, Bhavya Minesh Shah et al. (+3 more)
Robots collaborating with humans must convert natural
language goals into actionable, physically grounded decisions. For example, executing a command such as "go two meters to the right of the fridge" requires grounding semantic references, spatial relations, and metric constraints within a 3D scene. While recent
vision language models (VLMs) demonstrate strong semantic grounding capabilities, they are not explicitly designed to reason about metric constraints in physically defined spaces. In this work, we empirically demonstrate that state-of-the-art VLM-based grounding approaches struggle with complex metric-semantic
language queries. To address this limitation, we propose MAPG (Multi-
Agent Probabilistic Grounding), an agentic framework that decomposes
language queries into structured subcomponents and queries a VLM to ground each component. MAPG then probabilistically composes these grounded outputs to produce metrically consistent, actionable decisions in 3D space. We evaluate MAPG on the HM-EQA
benchmark and show consistent performance improvements over strong baselines. Furthermore, we introduce a new
benchmark, MAPG-Bench, specifically designed to evaluate metric-semantic goal grounding, addressing a gap in existing
language grounding evaluations. We also present a real-world
robot demonstration showing that MAPG transfers beyond simulation when a structured scene representation is available.
Read the full abstract ▾
All authors Swagat Padhan, Lakshya Jain, Bhavya Minesh Shah, Omkar Patil, Thao Nguyen, Nakul Gopalan
Machine Learning
Rigorous Error Certification for Neural PDE Solvers: From Empirical Residuals to Solution Guarantees
Amartya Mukherjee, Maxwell Fitzsimmons, David C. Del Rey Fernández et al. (+1 more)
Uncertainty quantification for partial differential equations is traditionally grounded in discretization theory, where solution error is controlled via mesh/grid refinement. Physics-informed neural networks fundamentally depart from this paradigm: they approximate solutions by minimizing residual losses at collocation points, introducing new sources of error arising from optimization, sampling, representation, and overfitting. As a result, the generalization error in the solution space remains an open problem. Our main theoretical contribution establishes generalization bounds that connect residual control to solution-space error. We prove that when neural approximations lie in a compact subset of the solution space, vanishing residual error guarantees convergence to the true solution. We derive deterministic and probabilistic convergence results and provide certified generalization bounds translating residual, boundary, and initial errors into explicit solution error guarantees.
Read the full abstract ▾
All authors Amartya Mukherjee, Maxwell Fitzsimmons, David C. Del Rey Fernández, Jun Liu
Machine Learning · Cross-listed from cs.CL
Optimal Splitting of Language Models from Mixtures to Specialized Domains
Skyler Seto, Pierre Ablin, Anastasiia Filippova et al. (+4 more)
Language models achieve impressive performance on a variety of knowledge,
language, and
reasoning tasks due to the scale and diversity of pretraining data available. The standard training recipe is a two-stage paradigm: pretraining first on the full corpus of data followed by specialization on a subset of high quality, specialized data from the full corpus. In the multi-domain setting, this involves continued pretraining of multiple models on each specialized domain, referred to as split model training. We propose a method for pretraining multiple models independently over a general pretraining corpus, and determining the optimal compute allocation between pretraining and continued pretraining using scaling laws. Our approach accurately predicts the loss of a model of size N with D pretraining and D' specialization
tokens, and extrapolates to larger model sizes and number of
tokens. Applied to
language model training, our approach improves performance consistently across common sense knowledge and
reasoning benchmarks across different model sizes and compute budgets.
Read the full abstract ▾
All authors Skyler Seto, Pierre Ablin, Anastasiia Filippova, Jiayuan Ye, Louis Bethune, Angelos Katharopoulos, David Grangier
Machine Learning · Cross-listed from math.OC
Fast and Effective Computation of Generalized Symmetric Matrix Factorization
Lei Yang, Han Wan, Min Zhang et al. (+1 more)
In this paper, we study a nonconvex, nonsmooth, and non-Lipschitz generalized symmetric
matrix factorization model that unifies a broad class of
matrix factorization formulations arising in machine learning, image science, engineering, and related areas. We first establish two exactness properties. On the modeling side, we prove an exact penalty property showing that, under suitable conditions, the
symmetry-inducing quadratic penalty enforces
symmetry whenever the penalty parameter is sufficiently large but finite, thereby exactly recovering the associated symmetric formulation. On the algorithmic side, we introduce an auxiliary-variable splitting formulation and establish an exact relaxation relationship that rigorously links stationary points of the original objective function to those of a relaxed potential function. Building on these exactness properties, we propose an average-type nonmonotone alternating updating method (A-NAUM) based on the relaxed potential function. At each iteration, A-NAUM alternately updates the two factor blocks by (approximately) minimizing the potential function, while the auxiliary block is updated in closed form. To ensure the convergence and enhance practical performance, we further incorporate an average-type nonmonotone line search and show that it is well-defined under mild conditions. Moreover, based on the Kurdyka-Łojasiewicz property and its associated exponent, we establish global convergence of the entire sequence to a stationary point and derive convergence rate results. Finally, numerical experiments on real
datasets demonstrate the efficiency of A-NAUM.
Read the full abstract ▾
All authors Lei Yang, Han Wan, Min Zhang, Ling Liang
Machine Learning · Cross-listed from cs.AI
D5P4: Partition Determinantal Point Process for Diversity in Parallel Discrete Diffusion Decoding
Jonathan Lys, Vincent Gripon, Axel Marmoret et al. (+4 more)
Discrete
diffusion models are promising alternatives to autoregressive approaches for text generation, yet their decoding methods remain under-studied. Standard autoregressive search procedures, such as beam search, do not directly apply to iterative denoising, where hypotheses are complete intermediate sequences rather than left-to-right prefixes. Furthermore, existing
diffusion decoding procedures only provide limited control over the diversity and coverage of retained hypotheses. In this work, we introduce D5P4, a beam-style decoding method tailored to discrete
diffusion models, which casts intermediate beam selection as MAP inference under a partitioned Determinantal Point Process. This yields a model-internal batch objective that balances quality and diversity without external verifiers. Experiments on open-ended generation, question answering, and mathematical
reasoning show that D5P4 improves diversity and pass@$k$ coverage while matching or surpassing baseline quality and fidelity
Read the full abstract ▾
All authors Jonathan Lys, Vincent Gripon, Axel Marmoret, Lukas Mauch, Fabien Cardinaux, Ghouthi Boukli Hacene, Bastien Pasdeloup
Machine Learning
Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection
Ruilin Li, Heming Zou, Xiufeng Yan et al. (+4 more)
Recent paradigms in Random Projection Layer (RPL)-based continual representation learning have demonstrated superior performance when building upon a pre-trained model (PTM). These methods insert a randomly initialized RPL after a PTM to enhance feature representation in the initial stage. Subsequently, a linear classification head is used for analytic updates in the continual learning stage. However, under severe domain gaps between pre-trained representations and target domains, a randomly initialized RPL exhibits limited expressivity under large domain shifts. While largely scaling up the RPL dimension can improve expressivity, it also induces an ill-conditioned feature
matrix, thereby destabilizing the recursive analytic updates of the linear head. To this end, we propose the
Stochastic Continual Learner with MemoryGuard Supervisory Mechanism (SCL-MGSM). Unlike random initialization, MGSM constructs the projection layer via a principled, data-guided mechanism that progressively selects target-aligned random bases to adapt the PTM representation to downstream tasks. This facilitates the construction of a compact yet expressive RPL while improving the numerical stability of analytic updates. Extensive experiments on multiple exemplar-free Class Incremental Learning (CIL)
benchmarks demonstrate that SCL-MGSM achieves superior performance compared to state-of-the-art methods.
Read the full abstract ▾
All authors Ruilin Li, Heming Zou, Xiufeng Yan, Zheming Liang, Jie Yang, Chenliang Li, Xue Yang
Machine Learning
SHAPCA: Consistent and Interpretable Explanations for Machine Learning Models on Spectroscopy Data
Mingxing Zhang, Nicola Rossberg, Simone Innocente et al. (+5 more)
In recent years, machine learning models have been increasingly applied to spectroscopic
datasets for chemical and biomedical analysis. For their successful adoption, particularly in clinical and safety-critical settings, professionals and researchers must be able to understand and trust the
reasoning behind model predictions. However, the inherently high dimensionality and strong collinearity of spectroscopy data pose a fundamental challenge to model explainability. These properties not only complicate model training but also undermine the stability and consistency of explanations, leading to fluctuations in feature importance across repeated training runs. Feature extraction techniques have been used to reduce the input dimensionality; these new features hinder the connection between the prediction and the original signal. This study proposes SHAPCA, an explainable machine learning pipeline that combines Principal Component Analysis (for dimensionality reduction) and Shapely Additive exPlanations (for post hoc explanation) to provide explanations in the original input space, which a practitioner can interpret and link back to the biological components. The proposed framework enables analysis from both global and local perspectives, revealing the spectral bands that drive overall model behaviour as well as the instance-specific features that influence individual predictions. Numerical analysis demonstrated the interpretability of the results and greater consistency across different runs.
Read the full abstract ▾
All authors Mingxing Zhang, Nicola Rossberg, Simone Innocente, Katarzyna Komolibus, Rekha Gautam, Barry O'Sullivan, Luca Longo, Andrea Visentin
Machine Learning
Hierarchical Latent Structure Learning through Online Inference
Ines Aitsahalia and Kiyohito Iigaya
Learning systems must balance generalization across experiences with discrimination of task-relevant details. Effective learning therefore requires representations that support both. Online latent-cause models support incremental inference but assume flat partitions, whereas hierarchical
Bayesian models capture multilevel structure but typically require offline inference. We introduce the Hierarchical Online Learning of Multiscale Experience Structure (HOLMES) model, a computational framework for hierarchical latent structure learning through online inference. HOLMES combines a variation on the nested Chinese Restaurant Process prior with sequential Monte Carlo inference to perform tractable trial-by-trial inference over hierarchical latent representations without explicit supervision over the latent structure. In simulations, HOLMES matched the predictive performance of flat models while learning more compact representations that supported one-shot backward transfer to higher-level latent categories. In a forward transfer task, HOLMES additionally achieved above-chance outcome prediction for stimuli with never-before-seen feature combinations, by exploiting abstract shape-level representations learned across diverse training instances. These results provide a tractable computational framework for discovering hierarchical structure in sequential data.
Read the full abstract ▾
Machine Learning
Adaptive Regime-Aware Stock Price Prediction Using Autoencoder-Gated Dual Node Transformers with Reinforcement Learning Control
Mohammad Al Ridhawi, Mahtab Haj Ali and Hussein Al Osman
Stock
markets exhibit regime-dependent behavior where prediction models optimized for stable conditions often fail during volatile periods. Existing approaches typically treat all
market states uniformly or require manual regime labeling, which is expensive and quickly becomes stale as
market dynamics evolve. This paper introduces an adaptive prediction framework that adaptively identifies deviations from normal
market conditions and routes data through specialized prediction pathways. The architecture consists of three components: (1) an autoencoder trained on normal
market conditions that identifies anomalous regimes through reconstruction error, (2) dual node
transformer networks specialized for stable and event-driven
market conditions respectively, and (3) a Soft Actor-Critic reinforcement learning controller that adaptively tunes the regime detection threshold and pathway blending weights based on prediction performance feedback. The reinforcement learning component enables the system to learn adaptive regime boundaries, defining anomalies as
market states where standard prediction approaches fail. Experiments on 20 S&P 500 stocks spanning 1982 to 2025 demonstrate that the proposed framework achieves 0.68% mean absolute percentage error (MAPE) for one-day predictions without the reinforcement controller and 0.59% MAPE with the full adaptive system, compared to 0.80% for the baseline integrated node
transformer. Directional accuracy reaches 72% with the complete framework. The system maintains robust performance during high-
volatility periods, with MAPE below 0.85% when baseline models exceed 1.5%. Ablation studies confirm that each component contributes meaningfully: autoencoder routing accounts for 36% relative MAPE degradation upon removal, followed by the SAC controller at 15% and the dual-path architecture at 7%.
Read the full abstract ▾
Machine Learning
From Inference Efficiency to Embodied Efficiency: Revisiting Efficiency Metrics for Vision-Language-Action Models
Zhuofan Li, Hongkun Yang, Zhenyang Chen et al. (+3 more)
Vision-
Language-Action (VLA) models have recently enabled
embodied agents to perform increasingly complex tasks by jointly
reasoning over visual, linguistic, and motor modalities. However, we find that the prevailing notion of “efficiency” in current VLA research, characterized by parameters, FLOPs, or
token decoding throughput, does not reflect actual performance on robotic platforms. In real-world execution, efficiency is determined by system-level
embodied behaviors such as task completion time, trajectory smoothness, cumulative joint rotation, and motion energy. Through controlled studies across model compression,
token sparsification, and action sequence compression, we make several observations that challenge common assumptions. (1) Methods that reduce computation under conventional metrics often increase end-to-end execution cost or degrade motion quality, despite maintaining task success rates. (2) System-level
embodied efficiency metrics reveal performance differences in the learned action policies that remain hidden under conventional evaluations. (3) Common adaptation methods such as in-context prompting or supervised fine-tuning show only mild and metric-specific improvements in
embodied efficiency. While these methods can reduce targeted
embodied-efficiency metrics such as jerk or action rate, the resulting gains may come with trade-offs in other metrics, such as longer completion time. Taken together, our results suggest that conventional inference efficiency metrics can overlook important aspects of
embodied execution. Incorporating
embodied efficiency provides a more complete view of policy behavior and practical performance, enabling fairer and more comprehensive comparisons of VLA models.
Read the full abstract ▾
All authors Zhuofan Li, Hongkun Yang, Zhenyang Chen, Yangxuan Chen, Yingyan Lin, Chaojian Li
Machine Learning
On Optimizing Multimodal Jailbreaks for Spoken Language Models
Aravind Krishnan, Karolina Stańczak and Dietrich Klakow
As Spoken
Language Models (SLMs) integrate
speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone while introducing an expanded attack surface. SLMs have been previously shown to be susceptible to jailbreaking, where
adversarial prompts induce harmful responses. Yet existing attacks largely remain unimodal, optimizing either text or audio in isolation. We explore gradient-based
multimodal jailbreaks by introducing JAMA (Joint Audio-text
Multimodal Attack), a joint
multimodal optimization framework combining Greedy Coordinate Gradient (GCG) for text and Projected Gradient Descent (PGD) for audio, to simultaneously perturb both modalities. Evaluations across four state-of-the-art SLMs and four audio types demonstrate that JAMA surpasses unimodal jailbreak rate by 1.5x to 20x. We analyze the operational dynamics of this joint attack and show that a sequential approximation method makes it 4x to 6x faster. Our findings suggest that unimodal safety is insufficient for robust SLMs. The code and data are available at https://repos.lsv.uni-saarland.de/akrishnan/
multimodal-jailbreak-slm.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
How Uncertainty Estimation Scales with Sampling in Reasoning Models
Maksym Del, Markus Kängsepp, Marharyta Domnich et al. (+4 more)
Uncertainty estimation is critical for deploying
reasoning language models, yet remains poorly understood under extended chain-of-thought
reasoning. We study parallel sampling as a fully black-box approach using verbalized confidence and self-consistency. Across three
reasoning models and 17 tasks spanning mathematics, STEM, and humanities, we characterize how these signals scale. Both self-consistency and verbalized confidence scale in
reasoning models, but self-consistency exhibits lower initial discrimination and lags behind verbalized confidence under moderate sampling. Most uncertainty gains, however, arise from signal combination: with just two samples, a hybrid
estimator improves AUROC by up to $+12$ on average and already outperforms either signal alone even when scaled to much larger budgets, after which returns diminish. These effects are domain-dependent: in mathematics, the native domain of RLVR-style post-training,
reasoning models achieve higher uncertainty quality and exhibit both stronger complementarity and faster scaling than in STEM or humanities.
Read the full abstract ▾
All authors Maksym Del, Markus Kängsepp, Marharyta Domnich, Ardi Tampuu, Lisa Yankovskaya, Meelis Kull, Mark Fishel
Machine Learning · Cross-listed from cs.CR
FedTrident: Resilient Road Condition Classification Against Poisoning Attacks in Federated Learning
Sheng Liu and Panos Papadimitratos
FL has emerged as a transformative paradigm for ITS, notably camera-based Road Condition Classification (RCC). However, by enabling collaboration, FL-based RCC exposes the system to
adversarial participants launching Targeted Label-Flipping Attacks (TLFAs). Malicious clients (vehicles) can relabel their local training data (e.g., from an actual uneven road to a wrong smooth road), consequently compromising global model predictions and jeopardizing transportation safety. Existing countermeasures against such poisoning attacks fail to maintain resilient model performance near the necessary attack-free levels in various attack scenarios due to: 1) not tailoring poisoned local model detection to TLFAs, 2) not excluding malicious vehicular clients based on historical behavior, and 3) not remedying the already-corrupted global model after exclusion. To close this research gap, we propose FedTrident, which introduces: 1)
neuron-wise analysis for local model misbehavior detection (notably including attack goal identification, critical feature extraction, and GMM-based model clustering and filtering); 2) adaptive client rating for client exclusion according to the local model detection results in each FL round; and 3) machine unlearning for corrupted global model remediation once malicious clients are excluded during FL. Extensive evaluation across diverse FL-RCC models, tasks, and configurations demonstrates that FedTrident can effectively thwart TLFAs, achieving performance comparable to that in attack-free scenarios and outperforming eight baseline countermeasures by 9.49% and 4.47% for the two most critical metrics. Moreover, FedTrident is resilient to various malicious client rates, data heterogeneity levels, complicated multi-task, and dynamic attacks.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
SAVeS: Steering Safety Judgments in Vision-Language Models via Semantic Cues
Carlos Hinojosa, Clemens Grange and Bernard Ghanem
Vision-
language models (VLMs) are increasingly deployed in real-world and
embodied settings where safety decisions depend on visual context. However, it remains unclear which visual evidence drives these judgments. We study whether
multimodal safety behavior in VLMs can be steered by simple semantic cues. We introduce a semantic steering framework that applies controlled textual, visual, and cognitive interventions without changing the underlying scene content. To evaluate these effects, we propose SAVeS, a
benchmark for situational safety under semantic cues, together with an evaluation protocol that separates behavioral refusal, grounded safety
reasoning, and false refusals. Experiments across multiple VLMs and an additional state-of-the-art
benchmark show that safety decisions are highly sensitive to semantic cues, indicating reliance on learned visual-linguistic associations rather than grounded visual understanding. We further demonstrate that automated steering pipelines can exploit these mechanisms, highlighting a potential vulnerability in
multimodal safety systems.
Read the full abstract ▾
Machine Learning
Position: Spectral GNNs Are Neither Spectral Nor Superior for Node Classification
Qin Jiang, Chengjia Wang, Michael Lones et al. (+2 more)
Spectral Graph Neural Networks (Spectral GNNs) for node classification promise frequency-domain filtering on graphs, yet rest on flawed foundations. Recent work shows that graph
Laplacian eigenvectors do not in general have the key properties of a true
Fourier basis, but leaves the empirical success of Spectral GNNs unexplained. We identify two theoretical glitches: (1) commonly used "graph
Fourier bases" are not classical
Fourier bases for graph signals; (2) (n-1)-degree
polynomials (n = number of nodes) can exactly interpolate any spectral response via a Vandermonde system, so the usual "
polynomial approximation" narrative is not theoretically justified. The effectiveness of GCN is commonly attributed to spectral low-pass filtering, yet we prove that low- and high-pass behaviors arise solely from message-passing dynamics rather than Graph
Fourier Transform-based spectral formulations. We then analyze two representative directed spectral models, MagNet and HoloNet. Their reported effectiveness is not spectral: it arises from implementation issues that reduce them to powerful MPNNs. When implemented consistently with the claimed spectral
algorithms, performance becomes weak. This position paper argues that: for node classification, Spectral GNNs neither meaningfully capture the graph spectrum nor reliably improve performance; competitive results are better explained by their equivalence to MPNNs, sometimes aided by implementations inconsistent with their intended design.
Read the full abstract ▾
All authors Qin Jiang, Chengjia Wang, Michael Lones, Dongdong Chen, Wei Pang
Machine Learning
Communication-Efficient and Robust Multi-Modal Federated Learning via Latent-Space Consensus
Mohamed Badi, Chaouki Ben Issaid and Mehdi Bennis
Federated learning (FL) enables collaborative model training across distributed devices without sharing raw data, but applying FL to multi-modal settings introduces significant challenges. Clients typically possess heterogeneous modalities and model architectures, making it difficult to align feature spaces efficiently while preserving
privacy and minimizing communication costs. To address this, we introduce CoMFed, a Communication-Efficient Multi-Modal
Federated Learning framework that uses learnable projection
matrices to generate compressed latent representations. A latent-space regularizer aligns these representations across clients, improving cross-modal consistency and robustness to outliers. Experiments on human activity recognition
benchmarks show that CoMFed achieves competitive accuracy with minimal overhead.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CG
Hardness of High-Dimensional Linear Classification
Alexander Munteanu, Simon Omlor and Jeff M. Phillips
We establish new exponential in dimension lower bounds for the Maximum Halfspace Discrepancy problem, which models linear classification. Both are fundamental problems in computational geometry and machine learning in their exact and approximate forms. However, only $O(n^d)$ and respectively $\tilde O(1/\varepsilon^d)$ upper bounds are known and complemented by
polynomial lower bounds that do not support the exponential in dimension dependence. We close this gap up to polylogarithmic terms by reduction from widely-believed hardness
conjectures for Affine Degeneracy testing and $k$-Sum problems. Our reductions yield matching lower bounds of $\tilde\Omega(n^d)$ and respectively $\tilde\Omega(1/\varepsilon^d)$ based on Affine Degeneracy testing, and $\tilde\Omega(n^{d/2})$ and respectively $\tilde\Omega(1/\varepsilon^{d/2})$ conditioned on $k$-Sum. The first bound also holds unconditionally if the computational model is restricted to make sidedness queries, which corresponds to a widely spread setting implemented and optimized in many contemporary
algorithms and computing paradigms.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Fast and Interpretable Autoregressive Estimation with Neural Network Backpropagation
Anaísa Lucena, Ana Martins, Armando J. Pinho et al. (+1 more)
Autoregressive (AR) models remain widely used in time series analysis due to their interpretability, but convencional parameter estimation methods can be computationally expensive and prone to convergence issues. This paper proposes a Neural Network (NN) formulation of AR estimation by
embedding the autoregressive structure directly into a feedforward NN, enabling coefficient estimation through backpropagation while preserving interpretability. Simulation experiments on 125,000 synthetic AR(p) time series with short-term dependence (1 <= p <= 5) show that the proposed NN-based method consistently recovers model coefficients for all series, while Conditional Maximum Likelihood (CML) fails to converge in approximately 55% of cases. When both methods converge, estimation accuracy is comparable with negligible differences in relative error, R2 and, perplexity/likelihood. However, when CML fails, the NN-based approach still provides reliable estimates. In all cases, the NN
estimator achieves substantial computational gains, reaching a median speedup of 12.6x and up to 34.2x for higher model orders. Overall, results demonstrate that gradient-descent NN optimization can provide a fast and efficient alternative for interpretable AR parameter estimation.
Read the full abstract ▾
All authors Anaísa Lucena, Ana Martins, Armando J. Pinho, Sónia Gouveia
Machine Learning
When Differential Privacy Meets Wireless Federated Learning: An Improved Analysis for Privacy and Convergence
Chen Yaoling, Liang Hao and Tu Xiaotong
Differentially private wireless
federated learning (DPWFL) is a promising framework for protecting sensitive user data. However, foundational questions on how to precisely characterize
privacy loss remain open, and existing work is further limited by convergence analyses that rely on restrictive convexity assumptions or ignore the effect of gradient clipping. To overcome these issues, we present a comprehensive analysis of
privacy and convergence for DPWFL with general smooth non-convex loss objectives. Our analysis explicitly incorporates both device selection and mini-batch sampling, and shows that the
privacy loss can converge to a constant rather than diverge with the number of iterations. Moreover, we establish convergence guarantees with gradient clipping and derive an explicit
privacy-utility trade-off. Numerical results validate our theoretical findings.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models
Quentin Guimard, Federico Bartsch, Simone Caldarella et al. (+3 more)
Models that bridge
vision and
language, such as CLIP, are key components of
multimodal AI, yet their large-scale, uncurated training data introduce severe social and spurious biases. Existing post-hoc debiasing methods often operate directly in the dense CLIP
embedding space, where bias and task-relevant information are highly entangled. This
entanglement limits their ability to remove bias without degrading semantic fidelity. In this work, we propose Sparse
Embedding Modulation (SEM), a post-hoc, zero-shot debiasing framework that operates in a Sparse Autoencoder (SAE) latent space. By decomposing CLIP text
embeddings into disentangled features, SEM identifies and modulates bias-relevant
neurons while preserving query-relevant ones. This enables more precise, non-linear interventions. Across four
benchmark datasets and two CLIP backbones, SEM achieves substantial
fairness gains in
retrieval and zero-shot classification. Our results demonstrate that sparse latent representations provide an effective foundation for post-hoc debiasing of
vision-
language models.
Read the full abstract ▾
All authors Quentin Guimard, Federico Bartsch, Simone Caldarella, Rahaf Aljundi, Elisa Ricci, Massimiliano Mancini
Machine Learning · Cross-listed from cs.CR
Towards Verifiable AI with Lightweight Cryptographic Proofs of Inference
Pranay Anchuri, Matteo Campanelli, Paul Cesaretti et al. (+4 more)
When large AI models are deployed as cloud-based services, clients have no guarantee that responses are correct or were produced by the intended model. Rerunning inference locally is infeasible for large models, and existing cryptographic proof systems – while providing strong correctness guarantees – introduce prohibitive prover overhead (e.g., hundreds of seconds per query for billion-parameter models). We present a verification framework and protocol that replaces full cryptographic proofs with a lightweight, sampling-based approach grounded in statistical properties of neural networks. We formalize the conditions under which trace separation between functionally dissimilar models can be leveraged to argue the security of verifiable inference protocols. The prover commits to the execution trace of inference via Merkle-tree-based vector commitments and opens only a small number of entries along randomly sampled paths from output to input. This yields a protocol that trades soundness for efficiency, a tradeoff well-suited to
auditing, large-scale deployment settings where repeated queries amplify detection probability, and scenarios with rationally incentivized provers who face penalties upon detection. Our approach reduces proving times by several orders of magnitude compared to state-of-the-art cryptographic proof systems, going from the order of minutes to the order of milliseconds, with moderately larger proofs. Experiments on ResNet-18 classifiers and Llama-2-7B confirm that common architectures exhibit the statistical properties our protocol requires, and that natural
adversarial strategies (gradient-descent reconstruction, inverse transforms, logit swapping) fail to produce traces that evade detection. We additionally present a protocol in the refereed delegation model, where two competing servers enable correct output identification in a logarithmic number of rounds.
Read the full abstract ▾
All authors Pranay Anchuri, Matteo Campanelli, Paul Cesaretti, Rosario Gennaro, Tushar M. Jois, Hasan S. Kayman, Tugce Ozdemir
Machine Learning · Cross-listed from cs.CL
Hypothesis-Conditioned Query Rewriting for Decision-Useful Retrieval
Hangeol Chang, Changsun Lee, Seungjoon Rho et al. (+2 more)
Retrieval-Augmented Generation (RAG) improves Large
Language Models (LLMs) by grounding generation in external, non-parametric knowledge. However, when a task requires choosing among competing options, simply grounding generation in broadly relevant context is often insufficient to drive the final decision. Existing RAG methods typically rely on a single initial query, which often favors topical relevance over decision-relevant evidence, and therefore retrieves background information that can fail to discriminate among answer options. To address this issue, here we propose Hypothesis-Conditioned Query Rewriting (HCQR), a training-free pre-
retrieval framework that reorients RAG from topic-oriented
retrieval to evidence-oriented
retrieval. HCQR first derives a lightweight working hypothesis from the input question and candidate options, and then rewrites
retrieval into three targeted queries that seek evidence to: (1) support the hypothesis, (2) distinguish it from competing alternatives, and (3) verify salient clues in the question. This approach enables context
retrieval that is more directly aligned with answer selection, allowing the generator to confirm or overturn the initial hypothesis based on the retrieved evidence. Experiments on MedQA and MMLU-Med show that HCQR consistently outperforms single-query RAG and re-rank/filter baselines, improving average accuracy over Simple RAG by 5.9 and 3.6 points, respectively. Code is available at https://anonymous.4open.science/r/HCQR-1C2E.
Read the full abstract ▾
All authors Hangeol Chang, Changsun Lee, Seungjoon Rho, Junho Yeo, Jong Chul Ye
Machine Learning
AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science
An Luo, Jin Du, Xun Xian et al. (+12 more)
Data science plays a critical role in transforming complex data into actionable insights across numerous domains. Recent developments in large
language models (LLMs) and artificial intelligence (AI)
agents have significantly automated data science workflow. However, it remains unclear to what extent AI
agents can match the performance of human experts on domain-specific data science tasks, and in which aspects human expertise continues to provide advantages. We introduce AgentDS, a
benchmark and competition designed to evaluate both AI
agents and human-AI collaboration performance in domain-specific data science. AgentDS consists of 17 challenges across six industries: commerce, food production, healthcare, insurance, manufacturing, and retail banking. We conducted an open competition involving 29 teams and 80 participants, enabling systematic comparison between human-AI collaborative approaches and AI-only baselines. Our results show that current AI
agents struggle with domain-specific
reasoning. AI-only baselines perform below the top quartile of competition participants, while the strongest solutions arise from human-AI collaboration. These findings challenge the narrative of complete automation by AI and underscore the enduring importance of human expertise in data science, while illuminating directions for the next generation of AI. Visit the AgentDS website here: https://agentds.org/ and open source
datasets here: https://huggingface.co/
datasets/lainmn/AgentDS .
Read the full abstract ▾
All authors An Luo, Jin Du, Xun Xian, Robert Specht, Fangqiao Tian, Ganghua Wang, Xuan Bi, Charles Fleming, Ashish Kundu, Jayanth Srinivasa, Mingyi Hong, Rui Zhang, Tianxi Li, Galin Jones, Jie Ding
Machine Learning · Cross-listed from cs.AI
Regret Bounds for Competitive Resource Allocation with Endogenous Costs
Rui Chai
We study online resource allocation among N interacting modules over T rounds. Unlike standard online optimization, costs are endogenous: they depend on the full allocation vector through an interaction
matrix W encoding pairwise cooperation and competition. We analyze three paradigms: (I) uniform allocation (cost-ignorant), (II) gated allocation (cost-estimating), and (III) competitive allocation via multiplicative weights update with interaction feedback (cost-revealing). Our main results establish a strict separation under
adversarial sequences with bounded variation: uniform incurs Omega(T) regret, gated achieves O(T^{2/3}), and competitive achieves O(sqrt(T log N)). The performance gap stems from competitive allocation's ability to exploit endogenous cost information revealed through interactions. We further show that W's
topology governs a computation-regret tradeoff. Full interaction (|E|=O(N^2)) yields the tightest bound but highest per-step cost, while sparse
topologies (|E|=O(N)) increase regret by at most O(sqrt(log N)) while reducing per-step cost from O(N^2) to O(N). Ring-structured
topologies with both cooperative and competitive links - of which the five-element Wuxing
topology is canonical - minimize the computation x regret product. These results provide the first formal regret-theoretic justification for decentralized competitive allocation in modular architectures and establish cost endogeneity as a fundamental challenge distinct from partial observability. Keywords: online learning, regret bounds, resource allocation, endogenous costs, interaction
topology, multiplicative weights, modular systems, Wuxing
topology
Read the full abstract ▾