Papers

The increasing number of vulnerabilities in operating systems, together with sophisticated kernel-level threats (e.g., rootkits), has weakened the effectiveness of traditional in-kernel protection mechanisms. Since these defenses operate at the same privilege level as the kernel, they share the same attack surface and can be bypassed once the kernel is compromised. Isolation-based security approaches provide stronger protection by separating security logic from the kernel, but strict isolation often introduces semantic gaps that limit system visibility and hinder timely threat detection. In this paper, we present LOOM, a lightweight out-of-band operating system monitoring architecture built on ARM TrustZone. By leveraging TrustZone's hardware-enforced isolation, LOOM establishes a tamper-resistant monitoring environment independent of the kernel. To bridge the semantic gap, we design a lightweight semantic reconstruction mechanism in the Secure World. It selectively captures the states and behavioral patterns of critical kernel objects, such as process control blocks and kernel modules. Additionally, LOOM introduces a dual-stage hazard prevention mechanism that combines atomic memory protection with an interrupt-driven adaptive agent to detect and mitigate kernel rootkit activities. An address translation cache is further incorporated to optimize repeated address access and reduce monitoring overhead. Overall, we develop a multi-layered collaborative architecture with platform, functional, and auxiliary layers for secure and efficient kernel monitoring. A prototype of LOOM has been implemented on the Phytium D2000 platform. Experimental results indicate that LOOM incurs negligible overhead while maintaining a strong monitoring capability. Furthermore, a security capability analysis based on CVE cases demonstrates that LOOM can detect and mitigate various kernel attacks.

LLMs are widely deployed through cloud-hosted inference services, where Just-in-Time (JIT) compilation is used to reduce recurring framework and GPU-launch overhead. JIT serving introduces a host-side control plane that selects compiled artifacts and orchestrates their execution on the GPU. Meanwhile, the shared cloud setting has motivated a growing body of bit-flip attacks (BFAs) against LLM/DNN inference. Most existing BFAs target model parameters or weights and require model-specific knowledge. A smaller body of work reduces this dependency by faulting executable code, yet still corrupts code that directly implements model computation, limiting their attack effect to inference depletion. We present JITterFlip, the first BFA targeting the host-side JIT serving control plane of GPU-based LLM inference. By faulting CPU-resident serving decisions rather than model computation, JITterFlip enables both gibberish output generation and a correct-output sponge attack. To identify exploitable targets in a large JIT compiler stack, JITterFlip develops a decision-guided fault-vulnerable code analysis. Across four text and multimodal LLM workloads, the identified vulnerable code faults exhibit cross-model transferability, produce gibberish outputs with PPL ratios of $15.45\times$ to $2.48{\times}10^{6}\times$, and demonstrate correct-output sponge attacks with latency amplification of $2.03\times$ to $181.90\times$. JITterFlip also bypasses recent BFA defenses for LLMs while retaining both attack effects. Last, we demonstrate end-to-end Rowhammer attacks across four LLMs: a single bit flip in CPU-resident branch code propagates across the CPU-GPU boundary to disrupt GPU-executed inference without direct access to GPU memory, reaching up to $7.23{\times}10^{6}\times$ PPL amplification or $124.97\times$ latency amplification while preserving the exact generated output.

Rehosting enables tight control and introspection for firmware testing, but existing approaches largely fail to reach deeper application states and cannot drive embedded protocol stacks beyond early-stage initialization. This limitation reflects a broader weakness in current rehosting techniques: their inability to faithfully model complex peripheral semantics and dependencies. In particular, existing work typically relies on passive approximations of peripheral behavior and overlooks three key aspects: (i) the interplay among interrupts, MMIO, and DMA; (ii) implicit state transitions within peripherals; and (iii) interactions across multiple peripherals. To address this challenge, we propose Reactive Peripheral Modeling (RPM), an abstraction that models hardware peripherals as reactive and stateful systems. RPM captures peripheral behavior using event-condition-action semantics, enabling faithful representation of interrupt, MMIO, and DMA scheduling, implicit state transitions, and cross-peripheral interactions. We implement RPM in Bluezz for BLE firmware rehosting and fuzzing, and show that reactive modeling is necessary to reach deep protocol states. We evaluate Bluezz on representative BLE stacks, including NimBLE, Zephyr, and Nordic SoftDevice, a closed-source commercial stack. Across 18 targets, Bluezz achieves an average basic-block coverage more than 2.6 times that of prior state-of-the-art rehosting approaches. Unlike prior approaches, which remain largely confined to advertising and scanning logic, Bluezz reliably exercises connected BLE states and uncovers five previously unknown vulnerabilities that manifest only after connection establishment. Finally, we show that RPM generalizes beyond BLE to other embedded firmware running on different MCUs.

Different attack methods follow different search trajectories, they succeed on different subsets of samples, whereas existing hard-label black-box text attacks mainly focus on improving individual attackers or manually combining them. We present OASIS, a method for optimizing attacker sequences in hard-label black-box text attacks. OASIS first performs a one-time bi-objective attack chain search over candidate sequences to balance attack success rate and perturbation, and then reuses the selected fixed global chain during attack chain execution. Experiments across multiple datasets, victim models, and large language models show that OASIS consistently outperforms strong standalone baselines and simple manually constructed chains. These results suggest that attacker composition is not merely an implementation choice, but a practical optimization target for improving hard-label black-box text attacks.

We present Adaptive Direction-Based Authentication (ADBA), a knowledge-based authentication method for Virtual Reality that decouples users' needs temporally by enforcing password creation based on virtual environment context while supporting both context- and digit-based entries during authentication. This design prioritizes memorability for new passwords and offers both efficient and memorable options to support users' evolving needs. We conducted a remote longitudinal study with 66 participants comparing ADBA against 6-digit PINs over 2-3 weeks. The results demonstrated that ADBA achieved superior memorability and lower perceived task load. Interestingly, no participant chose to enter via digits in the study, yet they still perceived ADBA to be highly efficiency despite longer objective entry times. ADBA also provided security benefits through randomly-generated digit representations, though some degree of password homogeneity was observed in specific virtual environments. Our findings suggest that ADBA offers solid advantages to the traditional PINs, and successfully addresses the tradeoffs between efficiency, memorability, and security under the usage scenarios considered in the study.

Aerial object detection is increasingly deployed in real-world applications, but models remain vulnerable to physical, universal adversarial patches that cause them to miss objects. Furthermore, defenders face the practical constraint of training data scarcity: aerial imagery is costly to collect and label, so a deployment site typically yields hundreds of images rather than the tens of thousands that adversarial robustness benchmarks assume. To tackle model vulnerability and training data scarcity, we propose Adversarial Robustness with Manifold-Oriented Training (ARMOR), a novel defense that realizes the core insights of on-manifold adversarial training (OMAT) in low-data regimes. ARMOR builds on the insight of OMAT to model the data manifold - the compact structure capturing the data's relevant features - to learn and robustify these features during training. While OMAT relies on the data-intensive operations of training large generative models and adversarial training to achieve this, ARMOR adopts a data-efficient approach that reuses labels the detection task already supplies: ARMOR (i) masks image backgrounds to retain object-relevant features, and (ii) injects randomized patches on objects to improve feature robustness. Our low-data experiments with physically-realizable adversarial patches evaluate both query-free transfer attacks and defense-aware attacks. ARMOR maintains strong clean performance of over 0.90 model confidence, while improving adversarial robustness by up to 0.32 in model confidence over state-of-the-art defenses. Physical experiments with printed patches confirm that these gains survive deployment. Overall, ARMOR translates insights from manifold-based training to defend object detectors amidst training data scarcity.

Visual environmental risk recognition plays an important role in secure authentication, where a user's surroundings may reveal sensitive information or introduce potential security risks. However, existing evaluations of multimodal large language models (MLLMs) rarely examine whether models can reliably recognize, localize, and explain such risks in spatially grounded authentication scenarios. We present SpatialTrust, a question-answering benchmark for evaluating environmental risk recognition in secure authentication. SpatialTrust assesses five complementary abilities: sensitive factor detection, direct factor identification, indirect factor identification, direct factor explanation, and indirect factor explanation. We evaluate both proprietary and open-source MLLMs and find that current models show limited performance, especially in understanding and explaining indirect risks, indicating that spatial risk awareness remains a challenging capability for MLLMs. In addition, we introduce SpatialTrustGuard, a structured QA-and-audit pipeline that improves Qwen3-VL-30B-A3B-Instruct from 36.78% to 41.12% overall. Our findings highlight the need for dedicated benchmarks and structured inference methods to improve the trustworthiness of MLLMs in secure authentication.

Modern AI agents routinely cross trust boundaries: they ingest untrusted content, combine it with privileged instructions, persist intermediate beliefs in long-term memory, and invoke privileged tools. This creates an attack surface in which malicious payloads can enter through model inputs and cause harmful tool actions. Yet current governance stacks remain application-level middleware that share a process trust boundary with the agents they monitor. We argue that agents need an operating-system substrate providing mandatory, non-bypassable services for identity, input mediation, memory governance, and execution control. We introduce AgentKernel, a trust-native agent operating system built around the premise that security must be a first-class design constraint. AgentKernel wraps the agent lifecycle in a mandatory enforcement boundary organized into four pillars: Identity, Perception, Cognition, and Execution. Each pillar adapts classical OS security principles to failures at the semantic plane, including delegation abuse, prompt injection, memory poisoning, and tool misuse. AgentKernel treats structural security as a capability multiplier. Kernel-managed identity supports trustworthy cross-organization collaboration; graduated perception replaces brittle single-point filters; information-flow-controlled memory improves retrieval fidelity while limiting poisoning; and semantic-to-kernel enforcement permits broader tool privileges behind a non-bypassable boundary. We position AgentKernel as the missing OS layer beneath orchestration frameworks, agent runtimes, governance platforms, and execution sandboxes, and use systematic comparison and security analysis to show how a single integrated architecture can enforce security across the full agent lifecycle.

Quantum encrypted cloning encodes an unknown state into several encrypted components, each offering an alternative way to recover it later. We show that this redundancy can also serve for one-shot fault diagnosis: instead of inspecting the encrypted state, we measure relational Pauli observables testing consistency conditions imposed by the encoding. The canonical Yamaguchi–Kempf scheme encodes the input into \(n\) signal–key pairs, all carrying the same coherent Bell label, plus a transformed copy of the input qubit. Comparing the labels of two pairs yields a deterministic check that localizes an anomalous pair and identifies its Pauli-error class without revealing the label. Such checks cannot tell whether the signal or the key of that pair is faulty, and no measurement on the pairs can (we prove that they already generate the whole group of deterministic state-blind observables supported there, of rank \(2(n-1)\)). This ambiguity matters: a faulty signal costs one redemption path, a faulty key threatens them all. However, retaining also the transformed input qubit contributes exactly two further independent checks, at any multiplicity, and these suffice to identify any single fault drawn from the single-qubit Pauli set. For three clones this gives six checks in all, and we prove that no smaller set of state-blind observables achieves the same resolution. Across clone multiplicities, parity governs how many components must be measured jointly to reach this resolution, not the resolution itself. These findings are then abstracted into a general framework — state-blind observables, deterministic healthy references, syndrome-induced fault partitions, redemption-oriented sufficiency — yielding relational diagnosability: a syndrome need not identify every fault, only enough of it to select a safe redemption path.

A benchmark score is a joint property of the model, the evaluation harness, the elicitation budget, the sampled population, and contamination status. Leaderboards publish the model and the score, so capability and leakage stay observationally equivalent. Existing taxonomies classify contamination for automated detection, not the question a reporter faces at publication: given the mitigations already applied, which validity threats remain open? We introduce a taxonomy organized by the mitigation each type defeats – direct, derivative, temporal, distributional, and acquired – spanning training-time and evaluation-time leakage. Holding out a private test set closes the first alone. The fifth is acquired during the evaluation itself; because it is a property of one run, it must be recorded with the reported score rather than with the benchmark release. We operationalize it as a four-field disclosure protocol in which "unknown" is a valid entry, released under CC BY 4.0 with a JSON Schema, a validator, and worked examples. Two coders external to the design team applied a pre-registered instrument to 41 documents. Per-variable linear-weighted $\kappa$ runs from 0.00 to 0.35 (median 0.21) over 29 main-pass documents against a single-coder test-retest ceiling of 0.84, collapsing under the class skew the registration anticipated; pooling raises it to 0.46 through chance correction rather than better agreement. Two variables fall below the prevalence-robust threshold registered in advance: strata reporting and the acquired type introduced here. Disagreement concentrates on when a variable applies rather than on what a document states. Elicitation budgets are reported in 13% of documents, and no document addresses all five types. The contribution is the taxonomy, the score-side artifact that follows from it, and a pre-registered measurement of instrument reliability and current disclosure.

When coding agents encounter defective test infrastructure they may reward-hack: hardcoding outputs or editing test files to pass tests they cannot legitimately satisfy, a pattern that has now appeared outside benchmarks, in a coordinated multi-agent intrusion of a major AI platform's production infrastructure. The same capability that lets an agent detect and exploit a defect could let it report one, given the right decision environment. We evaluate escalation channels, structured reporting tools available to the agent at the point of conflict, as a decision-environment intervention that both reduces reward hacking and surfaces the infrastructure defects that trigger it. A $2 \times 2$ factorial separates the contributions of an escalation tool, a standalone anti-reward-hacking policy, and their combination. Across 8 frontier models spanning 5 families, the combined intervention reduces reward hacking from 23.6% to 5.3% (mixed-effects logistic OR = 9.2, 95% CI 5.0–16.8, $p < 10^{-12}$) with no detectable cost or performance overhead, eliminating it entirely for 6 of 8 models. Escalation and hacking are near-perfectly mutually exclusive, with 98.7% of escalations involving no hacking (100% under the combined intervention). Beyond reduction, escalation channels function as diagnostic infrastructure: on top of monitoring, escalation adds +10.1 percentage points of defect detection coverage and is more accurate once it fires (99.4% vs 85.8%). Unlike containment-based approaches that risk outpacing growing model capabilities, escalation channels redirect capability toward disclosure rather than exploitation.

AI agents are moving toward persistent, stateful execution across various applications, accumulating execution state and external effects that are costly to reconstruct after failures. Checkpoint and rollback (C/R) are becoming essential for recovery, yet their security implications remain largely unexplored. Correct rollback does not imply secure recovery: a faithfully restored checkpoint may resume an execution whose states, assumptions, and external effects never coexisted in any valid history. In this paper, we present the first systematic security study of checkpoint and rollback in existing agent systems. By examining representative agent C/R systems, we characterize the design space of existing C/R mechanisms and develop a general execution model that captures their recovery boundaries and state dependencies. From this model, we identify five fundamental failure modes spanning incomplete or inconsistent internal state, stale external dependencies, nondeterministic replay, and unrecorded external effects. We further demonstrate their security impact through three end-to-end attacks on Hermes, Cline, and LangGraph, enabling malware-verification bypass, unauthorized mail forwarding, and double payment. To systematically study these failures in practice, we develop a multi-agent analysis pipeline that reconstructs execution semantics, identifies violations of the five failure conditions, and validates them through actual rollback. Across five representative frameworks, our evaluation shows that these failures recur across heterogeneous C/R designs and stem from a common gap between the state restored by a checkpoint and the dependencies required for secure continuation.

Spatio-temporal graphs are widely used in modeling complex dynamic processes such as temporal forecasting, molecular dynamics, and healthcare monitoring. Recently, stringent privacy regulations such as GDPR and CCPA have introduced significant new challenges for existing spatio-temporal graph models, requiring complete unlearning of unauthorized data. Since each node in a spatio-temporal graph diffuses information globally across both spatial and temporal dimensions, existing unlearning methods primarily designed for static graphs and localized data removal cannot efficiently erase a single node without incurring costs nearly equivalent to full model retraining. To address this, we propose CallosumNet, a spatio-temporal graph unlearning framework biologically inspired by the corpus callosum structure. CallosumNet makes two key technical contributions: (1) it reconstructs subgraphs using biologically-inspired virtual edges; and (2) it restores interlinked spatio-temporal dependencies among subgraphs via a lightweight meta-graph integration layer. Empirical results on four diverse real-world datasets show that CallosumNet achieves complete unlearning while maintaining accuracy very close to the gold model. The code is publicly available at https://github.com/wenlu-lab/STGraphUnlearning.

Git commit signing, introduced in 2012, is one mechanism for establishing commit provenance in software supply chains, yet developer-controlled adoption remains rare and developers' experiences using it are understudied. To examine this experience, we conducted a three-month study with senior undergraduate and graduate computer science students (n = 22), whom we treat as proxies for junior developers. Participants configured commit signing independently, used it across four coursework projects, extended it to a second device, examined an external repository containing anomalous commits, and answered security-reasoning prompts. We found that while almost all participants successfully signed every commit and rated routine signing positively, many faced friction during setup, multi-device configuration, and repository verification. Despite signing all semester, they struggled to spot anomalous commits during verification, with over a quarter finding none. Additionally, nearly half expressed at least one misconception regarding signing guarantees or key management. Without isolating whether these difficulties stemmed from tooling, education, or understanding, we conclude that making signing easier is not enough to ensure effective security use. Rather, secure adoption also requires tools and education that support signature verification against authorized identities, interpretation of missing signatures and unknown keys, and correct reasoning about key-lifecycle operations.

Existing video watermarking systems are symmetric: the party that can verify a mark holds the extractor weights or generator secret and can therefore also embed one. Benchmarks confirm the consequence, reporting that white-box forgery defeats all evaluated methods. We present a training-free video watermark that removes the shared secret. The signer embeds a complete Ed25519 signature into the phase spectrum of the chroma plane; any party holding the 32-byte public key and public per-video metadata verifies offline, with no model, no registry, and no network. The payload, 1024 bits of signed message with error correction, is an order of magnitude above common learned payloads and is carried by three design elements: a run-length temporal layout whose decoder identifies payload groups by correlation and never reads a frame index, a payload-free search that recovers scale, rotation, and translation from the carrier itself, and a closed-loop signing procedure that selects each video's embedding strength by self-verification through the unchanged public verifier. On 1000 uncurated real-world clips the system ships a verifying signature for 99.3% of the corpus and accepts a wrong public key zero times in 1000 attempts. An attack-aware acceptance gate yields embeddings that survive H.264 re-encoding at 100% and 50% rescaling at 97.4% on gated clips. The signature also verifies through a real display and capture loop, an axis absent from published evaluations.

However, no known work considered the functionality requirement in its most realistic setting. We propose a new security definition of BAEKS in the multi-user (with adaptive corruptions) and multi-challenge (both in terms of ciphertext and trapdoor in an interleaved manner) settings. We also study the question of the unforgeability of BAEKS. In fact, our strong hiding requirement already implies a significant amount of unforgeability. We then propose a new BAEKS construction in the bilinear pairing groups. We prove this scheme achieves adaptive tight full-hiding security under (almost) standard MDDH assumptions. Restricting our BAEKS construction for a single receiver also gives an efficient and tightly secure PAEKS construction. We further run experiments to implement and evaluate our scheme.

Feed-forward 3D Gaussian Splatting (3DGS) reconstructs a 3D scene from sparse images in one forward pass. Its shared pretrained weights also expose a supply-chain attack surface. Existing Neural Radiance Field and 3DGS backdoors modify individual scenes and activate at selected viewpoints; they do not install persistent behavior in shared generator weights. We introduce GhostSplat, an input-triggered backdoor that installs such behavior in feed-forward 3DGS. A low-amplitude pattern added to the input images causes the poisoned generator to render an attacker-chosen payload on unseen victim scenes. Anchoring the payload to a 3D point and reprojecting it into each target view makes the payload multi-view consistent. Exact projection onto the generator's representation-specific consistency set leaves a realized payload unchanged because the output already belongs to that set. The GhostSplat training framework succeeds across three architectures (MVSplat, pixelSplat, DepthSplat) and two datasets (RealEstate10K, ACID). Its strongest evaluated injection and deletion settings reach 96% and 100% ASR, respectively, with zero observed false positives while surviving JPEG, blur, and resampling. Defenses that use only that exact projection are therefore insufficient; effective mitigation requires information or intervention beyond same-set consistency projection.

Large Language Model (LLM) watermarks provide a mechanism for text provenance, enabling model owners to identify machine-generated content and attribute it to a specific watermarked model. However, current LLM watermarking approaches predominantly rely on inference-time sampler methods and focus their analysis on dense models. Inference-time methods are only effective when the text is explicitly generated via the model owner's controlled API; they fail in a post-compromise scenario. An adversary who steals or leaks the model weights gains complete control over inference and can simply run an unmodified sampler, bypassing the watermark and preventing post-theft attribution. In this work, we introduce Watermarking of Experts (WoE), a novel black-box text provenance method that leverages the unique structural properties of sparse Mixture-of-Experts (MoE) models. WoE biases the vocabulary of specific experts and shifts the watermark signal embedding away from unenforceable inference wrappers. This approach ensures the watermark remains intrinsic to the model parameters, enabling defenders to attribute text generated by stolen weights, leaked checkpoints, and secondary dense models distilled from the stolen architecture without needing access to the adversary's deployment or weights. We evaluate WoE across eight MoE models, demonstrating successful watermark detection from suspect text, achieving an average true positive rate of 90.1% at a 1% false positive rate, reaching up to 94.9%, while largely preserving general model utility. Furthermore, WoE remains detectable under adversarial supervised fine-tuning, model extraction, and output-level paraphrasing, forcing malicious actors into a trade-off in which weakening the attribution signal requires additional model adaptation or text-rewriting operations, or compromises the utility of the resulting output.

We ask whether a model protects a user in the same way when that user speaks rather than types. Using a single distress vignette—a physical injury of unstated severity following an interpersonal conflict—we present four frontier models with matched inputs across voice, text, and raw API deployment conditions (n=30 per cell) and code each response along five binary protective indicators, including whether the model issues an explicit medical-care directive. Voice-interface responses are markedly shorter than text-interface responses for three of the four models, and protective behavior contracts alongside that compression: medical directives are at ceiling under both the API and text conditions but decline under voice for every model tested. The contraction is not reducible to length. One model produces voice and text responses of comparable length yet still drops medical directives, and another falls below ceiling between its API and voice conditions, whose responses are of nearly identical length. Under raw API access the pattern is categorical rather than partial: no model asks after the user's safety even once. These results show that protective intervention is sensitive to the surface through which a request arrives, that this sensitivity is detectable using a simple protective coding scheme, and that it is not explained by turn length alone.

Security-token standards expose privileged controls without identifying the legal effect executed or the evidence and reversal obligations it carries. We formalize in Isabelle/HOL a reference execution semantics for the six ERC-8319 meanings: FREEZE, SEIZE, CONFISCATE, LIQUIDATE, RESTRICT, and RECOVER. It distinguishes applied, rejected, and operational-failure outcomes and mechanizes action-specific reversals, replay and epoch rules, complete frames, case-local terminality, and final receipts; the session builds without unproved placeholders or additional axioms. An indistinguishability theorem shows that bound kernel inputs cannot establish external facts about title, settlement, or entitlement. Constructive witnesses and direct mutations establish reachability and sensitivity for the declared fault set. For a successor ERC-TRUST Solidity/EVM candidate, we report separately scoped Foundry, Certora, Kontrol/KEVM, mutation, deterministic-build, runtime-identity, and independent-reproduction evidence. All twelve named evidence lanes pass with none pending, while the 74-row obligation ledger remains conditional: 70 rows are closed, two runtime-link rows remain successor obligations, and two are inapplicable. The Native runtime is bound separately from an ERC-3643 interoperability reference that explicitly reports Partial and full=false, not Verified Full. These results do not establish complete Isabelle-to-Solidity-to-EVM refinement, compiler correctness, audit completion, production readiness, deployment verification, or external legal truth. They provide a machine-checked domain semantics and an explicit map of proved, bounded, assumed, and open results.

Applications such as personalized assistance and proprietary document analysis require large language models (LLMs) to generate outputs from private data. Yet powerful LLMs typically cannot be deployed on the resource-constrained devices where private data resides, and uploading private data to cloud-hosted LLMs exposes sensitive information. Recent work addresses this tension with a cloud-edge collaborative decoding paradigm, where private data are kept on the edge with a small language model (SLM) producing next-token distributions, which are fused with predictions from a cloud LLM operating solely on public data. In this paper, we systematically analyze the privacy risks of such a paradigm with a novel evaluation framework using constructed QA datasets, which show that such collaboration can expose substantial private-context information. To address such privacy leakage, we propose CoVeil, a defense mechanism which dynamically optimizes transmitted signals to suppress leakage during decoding time while preserving the collaborative quality. Extensive evaluations demonstrate that CoVeil consistently improves the privacy-utility trade-off over existing baselines by reducing data leakage by up to 87.2%, with minimal accuracy loss.

Face authentication is widely deployed in security-sensitive applications, while increasingly realistic 3D spoofing attacks pose growing threats. High-fidelity 3D masks can reproduce facial appearance and geometry but cannot replicate the intrinsic physical responses of living tissue, which can be actively probed by wireless signals. However, the resulting liveness cues captured by wireless signals are entangled with user-dependent facial geometry, limiting cross-user generalization. We present UiAs, a multimodal user-independent 3D facial anti-spoofing system using electromagnetic (mmWave) and mechanical (acoustic) waves. The two modalities share similar user-dependent geometric variations, allowing UiAs to suppress them through cross-modal subtraction while preserving modality-specific liveness cues. Their complementary physical responses further improve live/spoof discrimination. In practical deployments, multiple materials (e.g., skin, hair, eyeglasses, or face coverings) may also bias liveness representations, while spoofing materials are diverse and open-ended. UiAs addresses both through skin-anchored contrastive learning. We evaluate UiAs with real 3D spoofing attacks, which achieves 93.25% accuracy for unseen users without user-specific physical-signal enrollment.

Linguistic steganography hides secret messages in natural language text. Large language models (LLMs) have reshaped the field, but a systematic account of how these scattered advances collectively reshape the field in this new era is still missing. We provide one along four axes: 148 steganographic methods, 60 linguistic steganalysis countermeasures, 23 evaluation metrics, and 9 open challenges, each with taxonomies, reviews, and adoption analyses. Cutting across these axes, we identify five specific paradigm shifts in the LLM era: (1) from covertext modification to prompt-only generation, (2) from heuristic to provable security, (3) from white-box symmetric LMs to black-box or asymmetric access, (4) from security-centric designs to joint optimization, and (5) from text-quality concerns to engineering issues. The survey aims to serve as both a reference and a roadmap for practical and responsible linguistic steganography in the LLM era.

Federated learning (FL) enables collaborative training without directly sharing raw data, but remains vulnerable to malicious clients. Voting-based FL improves robustness by partitioning clients into groups, training one model per group, and aggregating predictions by plurality voting. However, under class-disjoint non-IID data, distribution-oblivious grouping can yield highly variable certified accuracy (CA). We propose CARVY-FL, which estimates client distribution types from one-epoch model updates and uses anticlustering to increase within-group distributional diversity. Under a fixed grouping, CARVY-FL retains the voting-based CA guarantee while increasing vote margins. Experiments on MNIST and Fashion-MNIST show higher CA than FLCert. Under BadNets with model replacement, CARVY-FL improves the AUC of 100-ASR by 11.1% and 14.9%, respectively.

Diffusion models have become the dominant family of generative models in the visual domain. However, their widespread public availability enables misuse at scale, motivating a rapidly growing body of research on adversarial attacks and defenses. This survey provides, to our knowledge, the first unified review of this literature across three visual modalities: image, video, and 3D. We introduce a comprehensive, task-centric taxonomy: we first divide the literature by modality; within each modality, we separate methods into attacks and defenses, and then group them by the generative task they target, presenting them chronologically within each task. Moreover, we provide an in-depth analysis of their evaluation settings, consolidating the datasets, metrics, and benchmarks used to assess them. We conclude by identifying several open challenges and outlining concrete future research directions. Project Webpage: https://github.com/ozgurkara99/awesome-adv-attack-defense-on-diffusion

We introduce the Web-CLI, a novel application architecture deploying powerful computational capabilities (command-line tools compiled to WebAssembly, models run through client-side inference runtimes, and GPU-accelerated engines) as zero-install, offline-capable browser applications that preserve full underlying capability. Unlike web-based alternatives that require server-side processing and expose user data to third parties, Web-CLI applications execute entirely on the client, providing a verifiable privacy guarantee by architecture rather than policy. We define the pattern and its four properties: fidelity, progressive disclosure, offline-first, and zero egress. We present four reference implementations across distinct domains: ffmpeg-webCLI, a browser-based video editor built on FFmpeg; whisper-webCLI, speech transcription via Transformers.js; chat-webCLI, WebLLM-based language model inference; and 3mf-webCLI, a deterministic tool segmenting 3D models into multi-material files for physical 3D printing. Together they demonstrate that the pattern generalizes across deterministic media processing, neural speech recognition, LLM inference, and geometry processing with a physical output, and we outline how it extends to AI-native interfaces in which a local language model becomes the command surface itself. We further report early, anecdotal signs of independent reuse by third-party tools, suggesting the pattern generalizes beyond its reference implementations. We evaluate the primary implementation against native FFmpeg on performance and feature parity, and argue that progressive disclosure lowers the barrier for non-technical users. We argue that for applications processing sensitive user data (medical, legal, journalistic, or personal), the Web-CLI should be the default architecture, as it makes data locality an independently verifiable technical property rather than a policy promise.

Large-scale diffusion models have fueled numerous profitable downstream applications for AI-related businesses, including visual editing and content creation. Meanwhile, due to the huge amount of resource consumption (e.g., computation and high-quality data) during training, such diffusion models are deemed valuable intellectual property (IP) for tech companies like OpenAI and Google. Yet, the IP assets are vulnerable to various unauthorized uses by adversaries seeking to steal models for customized, usually commercial applications. Some existing approaches have explored IP protection for AI models; however, they mostly face structural limitations in common — using a training-time watermarking by injecting artifacts in the model, which can impose a measurable utility cost and can be weakened by post-hoc fine-tuning. To address these challenges, this work investigates IP protection (i.e., model ownership verification) for diffusion models in a realistic commercial scenario with minimal model utility loss. Specifically, the proposed method builds a framework for model ownership verification, termed “{Membership is Ownership} (MiO)”, based on a population-level hypothesis test on a private member evidence dataset. MiO verifies ownership using two criteria: model attribution through membership inference and model separation from public references. Both are tested at $p<10^{-6}$. We evaluate MiO on DDIM and Stable Diffusion models without modifying the owner model or its sampling pipeline, and report ROC-AUC and true-positive rates at fixed nominal false-positive targets. Furthermore, MiO stays stable under different post-theft fine-tuning and weight perturbation in adversarial scenarios, reflecting better robustness compared to the watermarking methods.

Behavioral biometric authentication (BBA) systems use deep learning models to transform biometric signals, such as eye movements, voice, keystroke/touchstroke dynamics, and gait, into identity embeddings for user authentication. While designed to encode identity, these embeddings may inadvertently reveal sensitive demographic attributes, including gender, age, and height. Consequently, an adversary with access to the authentication model can infer demographic information from biometric signals, including those of users unseen during training or enrollment. In this paper, we present the first systematic audit of demographic leakage in BBA systems, evaluating 11 models across 9 datasets spanning four biometric modalities. We further benchmark four post-hoc suppression methods-Incremental Variable Elimination (IVE), Hilbert-Schmidt Independence Criterion (HSIC), Adversarial Encoder-Decoder (AED), and Protected Attribute Suppression System (PASS) to assess their ability to mitigate demographic leakage while preserving authentication utility. Our analysis reveals substantial variation in leakage and suppressibility across modalities, model architectures, and learning objectives. While voice embeddings exhibit high leakage that can be effectively suppressed, keystroke/touchstroke embeddings exhibit lower leakage but are considerably more difficult to sanitize. These findings highlight a fundamental privacy risk in behavioral biometric authentication and provide insights into the factors governing demographic information suppressibility.

Detecting SQL Injection (SQLi) attacks ranks among the most critical challenges in web application security. This research conducted a systematic literature review to identify the research gaps in this domain and responsively designed and optimised a DistilBERT-Stacked Ensemble pipeline to improve detection efficiency and robustness while reducing false-positive and false-negative rates. Comprehensive pre-processing and tokenisation were performed, DistilBERT embeddings were extracted, and machine-learning and ensemble classifiers were trained and ranked on accuracy, precision, recall and F1-score. The three best performers (Logistic Regression, XGBoost and SVM) were combined through a neural meta-learner to form a stacked ensemble. The ensemble was hardened with adversarial examples generated by the Fast Gradient Sign Method (FGSM) and tuned with Optuna. The optimised ensemble achieved 99.81% across all reported metrics, closely comparable to the strongest single model (DistilBERT SVM, 99.82%). On the evaluation platform used in this study (Section 3.8), the ensemble classified the full test set in 0.0136s against 1.896s for DistilBERT-SVM, an approximately 140-fold reduction in measured inference latency, while retaining 99.77% accuracy under a single-step FGSM attack. The contribution is the design and validation of a SQLi detector performing with state-of-the-art accuracy at real-time speed and with demonstrated robustness to a single-step FGSM attack, rather than a marginal gain in accuracy. Sensitivity analysis further confirmed the stability of the model. These findings highlight the value of adversarial training and stacked meta-learning in building robust Web Application Firewalls (WAFs) for SQLi detection. For open validation, the dataset, test sets and models are made available at https://github.com/mlily2024/Final-project-SQL-injection-pipeline.

Detecting sophisticated SQL Injection (SQLi) attacks remains among the most critical challenges in web applications security. This research study has resulted in an optimised hybrid BERT-GNN pipeline with improved detection accuracy and robustness while reducing false-positive and false-negative rates. SQL queries are tokenised and encoded into contextual BERT embeddings, which then initialise the node features of a Graph Neural Network (GNN) trained to classify each query, with the architecture tuned by Optuna over accuracy, precision, recall, and F1-score. The proposed model achieved 99.67% accuracy, with 99.71% precision, 99.39% recall, and 99.55% F1-score on the attack class. A sensitivity analysis, performed by perturbing graph inputs, further assessed the model robustness and yielded a low mean sensitivity score of 0.0037, indicating stable predictions under such perturbations. The results have demonstrated the potential of a novel hybrid model that couples BERT contextual understanding with the GNN structural modelling to detect sophisticated SQLi attack vectors. For open validation, the dataset, test sets and models are made available at https://github.com/mlily2024/Final-project-SQL-injection-pipeline.