Papers

Cloud-edge Large Vision-Language Model (LVLM) inference enables efficient deployment by splitting computation between edge devices and cloud servers. In this process, intermediate vision tokens are transmitted from the edge to the cloud over a communication link, thereby exposing a new attack surface. We study vision token manipulation attack (VTM-Attack) under a black-box man-in-the-middle setting, where an adversary intercepts and manipulates a subset of transmitted vision tokens under a budget constraint. We propose four naïve attack strategies and an optimization-based token selection method. Experiments on 6 state-of-the-art LVLMs (3B-72B) across 4 benchmarks show that manipulating only 10% of vision tokens can reduce accuracy by up to 88.31%. These results reveal a critical vulnerability in cloud-edge LVLM inference.

There is no doubt that safety alignment is an essential step in LLM training. However, conceptually it does not distinguish between various domains and the level of potential harm of a query, which creates significant complications in the fields like cyber security, where a model should not be constrained by its safety circuits to accomplish the goals of legitimate, authorized operations. In this work, we share our findings from a large scale abliteration experiment on 24 open-source LLMs and show that domain-specific abliteration is achievable with standard methodology on the example of a 1T-parameter Kimi K2. Building on recent work showing that refusal in LLMs occupies a multi-dimensional subspace within layers, we find that it is also distributed widely across layers, especially in trillion-parameter MoE architectures, and so we aim to capture the part of it that represents harmful concepts in the cybersecurity domain exclusively. We also investigate the correlation between models' features and the effect of domain-specific abliteration, identifying that the type of safety training and architecture are the most reliable predictors. Finally, we classify the models into 3 abliteration susceptibility tiers and put forward a set of conjectures as to why a particular effect from this intervention might be observed in a given model.

Intrusion detection systems are often trained under static benchmark conditions, although deployed network environments are affected by traffic drift, sensor noise, changing workloads, and evolving attack behaviour. Under such distribution shifts, static detectors may produce confident but incorrect predictions, leading to silent and unsafe failure modes. In this paper, RES-DARE (Recursive Evolving Specialists-Digital Adaptive Reasoning Engine) is proposed as a failure-aware continual intrusion detection framework with rollback-safe self-repair. Difficult, uncertain, and misclassified samples are treated as failure signals for expert specialisation rather than being discarded as noise. A supervised contrastive encoder, two-pass expert router, failure-buffer mechanism, HDBSCAN-based failure-region discovery, and trust-risk monitor are integrated to support adaptive IDS behaviour. AEHM-v2 is introduced as a rollback-safe repair mechanism, where candidate adaptations are provisionally activated and committed only when macro-F1 is preserved or improved while trust risk remains stable. Otherwise, the system is rolled back to its last validated state. RES-DARE is evaluated on CICIDS2017, UNSW-NB15, and TON\_IoT, achieving macro-F1 scores of 0.9850, 0.9736, and 0.9691, respectively. Under Gaussian feature corruption at strength 0.10, RES-DARE retains an Attack-F1 of 0.7920 on CICIDS2017 and achieves near-zero catastrophic forgetting with F = 0.0015. The results show that RES-DARE improves robustness, warning capability, and deployment safety under degraded conditions.

Cybersecurity incident response has emerged as a critical area of interest for both researchers and practitioners. The corpus of literature on cybersecurity incident response is expanding, yet a unified framework for systematically organizing the accumulated knowledge remains absent. The aspects of incident response span multiple domains, including technology, human-computer interaction, organizational theory, and human factors. A comprehensive, integrative perspective on these factors can enable researchers to identify underexplored areas and more effectively target their empirical and theoretical investigations. Our study systematizes the factors that influence organizational preparedness for and response to cybersecurity incidents. Through a systematic review of academic literature (n = 417) and non-scientific publications (n = 40), we derived the "Cybersecurity Incident Response Influencing Factor Taxonomy" (CIR-IF Taxonomy). Existing empirical findings were classified within this taxonomy, providing a comprehensive and up-to-date overview of knowledge from the period 1999 to mid-2024. The taxonomy categories were systematically compared with seven established scientific frameworks and with the NIST Cyber Security Framework elements referenced in the NIST Special Publication 800-61r3 incident response profile. The results of this comparison show that the CIR-IF Taxonomy delivers a richer, more rigorous, and more systematically organized view of the factors that drive and shape incident response.

Application Programming Interfaces (APIs) are essential in software development, enabling web services, mobile apps, and microservices. However, their widespread use introduces significant security risks, highlighting the importance of API security. This paper presents HTTP REST API Learning (HRAL), a novel unsupervised anomaly detection approach that models the structure and behavior of API endpoints directly from network traffic, without relying on predefined rules or documentation. HRAL enables robust detection of malicious activity by understanding how APIs behave and flagging deviations as potential threats. We evaluate HRAL across varying levels of OpenAPI documentation detail and compare it with existing techniques. HRAL achieves strong performance, with an average recall of 82.07% and an F1-score of 87.24%, significantly outperforming alternatives when API documentation is limited. Moreover, our results approach the effectiveness of full API document definitions. When combined with signature-based rules such as the OWASP ModSecurity CRS, our system achieves 100% detection. These results highlight HRAL's effectiveness in real-world, partially documented API environments and its potential as a foundational layer for modern API security solutions.

Coding agents are capable; human oversight is the bottleneck. Unconstrained agents introduce security risks, erode codebase scalability, and make human review increasingly costly. We argue that the same methods used for decades to manage large human engineering teams: access control, network policies, strict coding conventions enforced by tooling; transfer directly to coding agents, and are cheaper (in token) than recent agentic scaffolding. We sketch a start-to-end system on this principle, and report a controlled experiment in scalable oversight: a small reviewer (Gemma 4 e4b) inspects a Python codebase containing 11 inserted backdoors. Recall rises from 54.5% (unconstrained, no tools) to 90.9% (constrained substrate plus a ~200-LoC `docs` CLI), with substrate and tools contributing independently. We choose Python deliberately: substrate-level oversight gains are largest where the language gives the fewest guarantees by default; the principles extend to languages like Rust.

LLM coding agents increasingly rely on third-party agent skills from public marketplaces, which execute with the agent's privileges and create a software supply-chain attack surface: a malicious skill can steal credentials, exfiltrate source code, or install backdoors. Existing defenses use static skill scanners based on pattern matching or LLM-as-judge analysis, but it remains unclear whether they withstand adaptive evasions that preserve malicious behavior while changing payload appearance. This paper first presents an adversarial study of existing skill scanners through SkillCloak, a payload-preserving evasion framework that keeps the attack semantics intact while transforming their visible form. SkillCloak uses two complementary strategies: Structural Obfuscation, which rewrites visible payload indicators into semantically equivalent forms, and Self-Extracting Skill (SFS) Packing, which hides malicious components from the install-time view and restores them during agent execution. Across eight scanners and 1,613 in-the-wild malicious skills, SFS Packing bypasses every scanner at over 90%, while Structural Obfuscation bypasses over 80% on most static scanners and reaches 96% on a hybrid scanner, showing that appearance-based auditing is insufficient. Motivated by this finding, we propose SkillDetonate, a behavior-centric runtime auditor that executes skills in a sandbox and detects malicious effects through OS-boundary information-flow evidence rather than install-time appearance. SkillDetonate combines on-demand closure lift, which observes instructions materialized during execution, with marker-based taint analysis, which tracks sensitive-data flows across the agent context, files, processes, and network operations. The results show that SkillDetonate detects 97% of attacks at a 2% false-positive rate and sustains 87% detection on real-world malicious skills.

We consider grassroots platforms – distributed systems of agents consisting of people identified by self-chosen public keys and their machines (smartphones) – and wish to make them secure against major faults: the loss of their private keys and/or their smartphones. As grassroots platforms have no global resource to rely on for recovery, our peer-based solution is based on: (\ia) a grassroots social graph in which agents establish and maintain friendships; (\ib) identity custodians, designated by each person, and (\ic) state custodians, which are grassroots platform-specific. Upon a person experiencing identity loss, and given a willing supermajority of the identity custodians of the person, the friends of the person replace the old public key with the new one across the graph and restore friendships, where all friends serve as state custodians for the social graph. Choosing a new keypair, obtaining a new smartphone, and convincing identity custodians to will a change of key all happen “off-chain”. Recovery from machine loss without loss of key (e.g. smartphone run over by truck, or its memory wiped) is simpler, requiring only the help of state custodians. We specify the social graph and its secure version as guarded multiagent atomic transactions, and implement the secure social graph via communicating volitional agents, an eventually synchronous message-passing model one step closer to implementation. We prove the implementation maps runs with recoverable faults to correct runs of the specification. We follow a similar path for grassroots coins and bonds, showing a common core as well as the platform-specific aspects of state recovery: a currency's single-writer log is recovered exactly, the recovered sovereign resuming without double-spending.

The society and emerging risk-based regulatory frameworks for AI underscore the need for rigorous risk assessment to ensure safe and reliable AI systems. In response to this imperative, this paper presents an overview of AI risk assessment (identification and analysis) and management methodologies. It begins by reviewing the worldwide regulatory landscape that drives the need for systematic AI risk assessment. Then we characterize the spectrum of AI-related risks identified in the literature, from technical failures to ethical and social impacts. Subsequently, it reviews key risk assessment methodologies proposed for AI systems, focusing on general frameworks. The paper highlights best practices and illuminates methodological gaps, highlighting areas for further research on AI risk assessment.

Distributed machine learning enables collaborative model training without centralizing data, but it also exposes learning processes to privacy leakage and malicious manipulation. Existing defenses typically address these threats in isolation and are often tailored to specific learning paradigms or model architectures, limiting their applicability in realistic deployments. In particular, federated learning and decentralized learning exhibit distinct adversarial surfaces that are rarely addressed within a unified framework. In this paper, we present a model-agnostic framework for adversary-resistant distributed learning that jointly addresses privacy preservation and malicious behavior across both federated and decentralized settings. Our approach combines paradigm-specific defense mechanisms with GPBACC, a privacy-enhancing coded computing technique applicable to arbitrary machine learning models. For federated learning, we integrate robust aggregation strategies to mitigate the impact of malicious participants, while for decentralized learning we employ approximate decode-and-compare and group testing techniques to enable lightweight verification and adversary isolation without relying on a trusted aggregator. Crucially, we evaluate the proposed framework through an explicit, attack-driven analysis. We implement representative privacy attacks and malicious behaviors, and empirically demonstrate that the combination of GPBACC with robust aggregation and verification mechanisms significantly reduces privacy leakage and improves resilience against active adversaries. These results suggest that privacy-enhancing coded computing, when combined with appropriate adversary-resistance strategies, provides a practical and deployable foundation for secure distributed machine learning.

As Large Language Models (LLMs) and agentic systems become integrated into real-world applications, ensuring their safety and security is critical. Guardrail systems that detect and block malicious instructions sent to and from an LLM are an essential component of AI security. However, researchers conducting black-box adversarial emulation against production AI systems often struggle to determine whether a guardrail block or an LLM rejection has occurred. This distinction is important because the techniques used to bypass guardrails can differ substantially from those used to bypass LLM safety alignment, and has a material impact on attack technique selection and optimization. We propose the first black-box guardrail reconnaissance methodology, which detects the presence of a guardrail within a target AI system through behavioral monitoring of HTTP, lexical, and timing signals, assuming only black-box access and zero prior knowledge of the guardrail or AI system. Experiments demonstrate that our approach detects guardrail presence with 100% accuracy, with statistically significant behavioral separation between benign and malicious interactions (q < 0.001). Our approach further identifies the content categories a guardrail is designed to block, and distinguishes guardrail blocks from LLM rejection on unseen prompts with an average F1 score of 98%.

We present HaloGuard 1.0, an open-weights implementation of the constitutional-classifier paradigm for input safety. It achieves state-of-the-art performance on English and multilingual prompt-safety benchmarks at roughly one-tenth the model size of current leading open guard models. The safety constitution is the organising structure of the corpus: a natural-language constitution of 46 policies and 2,940 subcategories drives synthetic data generation, with exhaustive one-to-one paired counterfactuals that hold topic and vocabulary fixed while flipping intent, a two-tier harmless design that separately targets boundary and baseline false positives (FPs), and balanced multilingual materialisation across 46 languages that treats language as a surface form appearing on both sides of the boundary rather than as an adversarial signal. Across seven prompt-safety benchmarks, HaloGuard 1.0-0.8B attains the best average F1 (90.9) of any open guard we evaluate, outperforming baselines up to 27B parameters (over 30 times larger) while holding false-positive rate (FPR) to 4.3 and false-negative rate (FNR) to 9.5. The HaloGuard 1.0-4B variant reaches average F1 of 92.1 and FPR of 3.5, spending its extra capacity on precision rather than recall. A structured adjudication of the remaining failures indicates that most apparent missed-harm cases are benchmark mislabels rather than genuine model misses. An always-on adversarial red-teaming protocol continuously hardens the guard against both content-level and agentic attacks. We release the models as open weights.

Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect unsafe, off-topic, or adversarial prompts. Existing guardrails predominantly rely on fine-tuning to build classifiers, which often suffer from low generalization and high inference latency. We present kNNGuard, a training-free guardrail that utilizes the activation space of an off-the-shelf LLM. Given a small bank of 50 safe and unsafe prompts, kNNGuard extracts hidden activations and performs multi-layer kNN fusing activation-space and embedding-space scores for classification. Across six domains spanning topical and security prompts, kNNGuard achieves competitive or superior F1 compared to fine-tuned state-of-the-art guardrails while running 2.7x faster than the best comparable guardrail, and 10x faster than a fine-tuned safety classifier without gradient updates or fine-tuning. Domain adaptation requires only updating the labeled bank, which can be constructed in under 10 seconds and several orders of magnitude faster than established guardrails. We also analyze the impact of system prompts, layer selection, and integration into production LLM pipelines as a configurable, low-latency guardrail.

Agentic systems enhance their capabilities by invoking external tools and maintaining persistent memory. However, these external dependencies introduce novel attack surfaces. Recent tool and memory poisoning attacks show that maliciously crafted tool descriptors and poisoned memory can covertly bias agent behavior. These threats reflect a deeper issue: the lack of verifiable continuity in the agent's contextual state for planning and execution. We present ElephantAgent, a protocol that enforces Contextual State Continuity to defend against contextual state poisoning. Inspired by prior state-continuity mechanisms (e.g., Nimble), ElephantAgent extends this protection to the evolving contextual state of agentic systems. We define the contextual state as the bounded, security-critical subset of the agent's entire context (e.g., tool state and memory). Before processing each query, ElephantAgent recomputes the digest of the local contextual state and verifies it against the latest authorized digest. Using replicated trusted hardware, ElephantAgent maintains a linearizable ledger of authorized contextual state transitions and detects out-of-band state tampering. To handle in-band semantic abuse, ElephantAgent additionally provides Historical Traceability, enabling conditional post-hoc audit and recovery to a known-good prior state.

Can a platform tell, before deployment, whether an open-weight checkpoint has had its refusal mechanism stripped? Runtime guards cannot: they score generations, not the artifact. We combine two cheap internal signals, a reference-anchored activation refusal-gap and a weight-recovery energy of the base-to-candidate weight difference, into a threshold-free checkpoint audit. The two are negatively correlated and label-complementary: the gap supplies refusal-specificity and the weight energy supplies recall. On a 273-checkpoint registry spanning Qwen, DeepSeek-distilled Qwen, Llama, and Gemma, their z-sum separates 57 public abliterations from 37 benign fine-tunes, merges, and instruction-tunes at AUROC 0.95, significantly above either signal alone (0.84, 0.90), and a Youden-calibrated threshold transfers to held-out families at balanced accuracy 0.89 (FPR 0.11), missing only 4 of 57. We then map two failures, in order of severity: a spoofed reference evades both axes with no training ({\Delta}W=0, h̊o}=1 by construction), and a white-box owner trains a checkpoint past the threshold while it stays guard-unsafe and coherent. The audit is effective triage, not tamper-proofing: it presumes an attested reference, and its claims are bounded by the registry we evaluate it on.

Smart contract vulnerabilities are predominantly logic bugs whose detection requires structured, step-by-step procedural knowledge of attack patterns and contract semantics. Existing LLM-based methods struggle to generate this knowledge automatically: prompt-based methods rely on manually crafted detection rules, while fine-tuning requires massive labeled datasets that are inherently scarce in this domain. We present EvoVuln, an automated framework that reformulates vulnerability detection as a procedural knowledge evolution problem, synthesizing and refining detection logic using only a minimal number of labeled samples. To achieve this, EvoVuln introduces two key mechanisms. First, a Runtime with an Inversion of Control (IoC) architecture compiles detection rules into Executable Policies. This strictly decouples deterministic control flow from LLM semantic reasoning, ensuring faithful logical adherence and producing dense diagnostic telemetry for precise error localization. Second, a two-phase evolution pipeline refines the rule via abductive semantic debugging without any parameter updates: Cold Start bootstraps and stress-tests an initial rule using auto-synthesized corner cases; Few-Shot Evolving then grounds the policy in real-world semantics using only five vulnerable and five safe examples per vulnerability type. Evaluated across five real-world vulnerability types, EvoVuln achieves a 71% macro-average F1-score, outperforming all baselines. The evolved procedural knowledge is portable across models: it enables a lightweight, low-cost model to surpass a much larger zero-shot model by 19 percentage points, and transfers to other LLMs without retraining, at a one-time evolution cost under $50.

Liquid democracy lets voters either vote directly or delegate their voting power to a trusted participant. Existing deployments make delegations publicly visible as they form, which invites popularity-driven herding, makes coercion verifiable, and leaves the election fragile when highly backed delegates abstain. We propose a liquid democracy mechanism that removes these vulnerabilities while keeping the tally fully auditable. Delegation choices are sealed with decentralized timed-release encryption while they are being formed and revealed in full for tallying, and each voter names ranked backup delegates together with a personal fallback ballot so that delegate failures do not silence them. We prove pre-reveal secrecy and resubmission receipt-freeness for the formation phase. Experiments grounded in real voting data show that the mechanism keeps voting power dispersed where transparent formation concentrates it into few hands, keeps outcomes stable under herding where transparent outcomes become a lottery on arrival order, and cuts vote loss under targeted delegate failures from 26% to about 3%. The experiments further characterize when delegation improves representational accuracy, namely when abstention is large, unrepresentative, and widely converted into delegation, giving deployments a concrete condition to assess.

Modern systems use format-, protocol-, and signature-based mechanisms before accepting artifacts across trust boundaries. These mechanisms are necessary: they show that an artifact is well formed, protocol-compliant, or properly authenticated. They do not, however, show that the artifact satisfies the semantic security properties required by the receiving domain. A signed update or an authenticated token may therefore be accepted yet enable compromise. We call this condition a Trust Boundary Semantic Gap (TBSG): an artifact crosses a trust boundary and passes correctly implemented syntactic validation, but the assertions established by that pass are insufficient to satisfy the receiving domain's security requirements. TBSG concerns what remains unestablished after a syntactic pass, not absent checks or implementation bugs. Analyzing 75 publicly reported security incidents (2014-2025) at the boundary level, we organize semantic misalignment into a four-dimensional analysis model: Identity, Spatial, Temporal, and Interpretation (MDTBSG). Building on it, we develop Trust Boundary Semantic Analysis and Mitigation (TBSAM), a design-time framework that identifies TBSGs from design specifications, prioritizes them, traces propagated gaps to their originating boundary, and maps each to candidate architectural controls. We apply TBSAM to a retrospective reconstruction of the SolarWinds/SUNBURST supply-chain attack, showing how it makes receiving-domain assumptions explicit, separates locally originating from propagated gaps, and identifies controls that interrupt the path. These results suggest that syntactic validation, while necessary, is not sufficient at trust boundaries, and that making trust-boundary assumptions explicit can complement Security-by-Design.

Recently, speech classification methods have gained widespread adoption in intelligent gadgets. Current study indicates that backdoor attacks provide a substantial security concern to these models, underscoring the pressing necessity to investigate additional potential attack techniques to expose and prevent such risks. This work discusses the vulnerability of current speech triggers to detection by deep neural network defenders and introduces the Timbre Leakage Attack (TLA). The suggested trigger disseminates timbre information at the frame level within the deep self-supervised features, producing poisoned samples that appear natural to human perception. Furthermore, we introduce Pmeta-TLA, an innovative training mechanism for embedding numerous backdoors one time. This method proposes a multi-backdoor injection training strategy using meta-learning and Projected Conflicting Gradients (PCGrad) and introduces TLA as a multi-target attack tool within it. We performed tests on data-poisoning backdoor attacks in keyword spotting tasks utilizing some deep neural network models. Experimental results indicate that the proposed strategy attains superior Attack efficacy, enhanced stealthiness, robustness, and a reduced attack cost relative to baseline methods.

Adversarial attacks on cybersecurity classifiers pose a dual threat: degrading predictions and destabilising the SHAP-based explanations that security analysts rely on to understand and triage alerts. We extend our prior MLP conference study to Random Forest and XGBoost across four tabular security datasets (phishing URLs, UNSW-NB15, NF-ToN-IoT, HIKARI-2021), evaluating five attacks including three black-box methods applicable to non-differentiable tree models. We introduce the Explainability Stability Index (ESI), a scalar metric computed from TreeSHAP attribution drift under adversarial perturbation, reported on the same [0,1] scale as the Robustness Index (RI). A key finding is that gradient-based black-box attacks (ZOO) produce degenerate results against XGBoost (apparent RI ~0.98) due to piecewise-constant prediction surfaces, while score-based Square Attack reveals genuine vulnerability (RI ~0.36). These degenerate perturbations still drive substantial attribution drift: XGBoost ESI ~0.06-0.16 despite near-perfect ZOO robustness, versus 0.14-0.29 for RF, showing that prediction robustness and explanation stability are distinct axes requiring joint measurement. A two-axis framework (gradient dependence, query efficiency) explains the observed attack ranking and yields practical guidance for tree ensemble evaluation. A step-size ablation explains a counterintuitive PGD anomaly on z-score normalised tabular data.

Hardware security verification is a multi-stage process in which engineers must navigate complex design analyses, threat considerations, and verification strategies. They often need security-focused guidance, yet current verification environments provide little structured support for such assistance. Although conversational AI could offer such on-demand assistance, directly using general-purpose chatbots like ChatGPT or Gemini is risky due to their tendency to hallucinate and their reliance on static, outdated knowledge. We present VeriChat, a domain-specialized conversational assistant designed to support, rather than replace, existing verification workflows by providing context-aware security guidance. VeriChat employs a retrieval-augmented, multi-agent workflow in which three specialized agents collaboratively minimize hallucinations while improving the transparency and reliability of the response. Beyond question answering, VeriChat integrates open-source EDA tools, including Icarus Verilog, Yosys, and SymbiYosys, to perform syntax checking, synthesis analysis, simulation, and formal verification directly on user-provided RTL designs. Evaluated using a comprehensive methodology, VeriChat achieves a Faithfulness score of 87.73%, significantly outperforming the leading proprietary models. We demonstrate the framework through a hardware Trojan detection case study on an AES S-Box IP, where VeriChat autonomously identifies, simulates, and formally proves a covert key-leakage vulnerability through a multi-turn conversational workflow.

LLM agents are increasingly developed as source-code applications built on agent frameworks. These agent programs combine conventional host-language code with framework-defined semantics for models, prompts, tools, memory, and multi-agent orchestration logic. As a result, their behavior depends not only on traditional control and data flows, but also on a new class of agent dependencies. Such dependencies are often expressed as framework-induced semantics, such as agent constructors, tool decorators, and agent handoff declarations, making them difficult to recover with existing static analysis or dependency tracking tools. In this paper, we present AgentFlow, the first static analysis framework for recovering and analyzing agent dependencies from agent programs. AgentFlow constructs an Agent Dependency Graph (ADG), a framework-agnostic graph representation that represents agents, prompts, models, capabilities, memory states, and control policies as typed nodes, and captures their component-dependency, control-flow, and data-flow dependencies as typed edges. Built on ADGs, AgentFlow supports a range of analyses for agent governance and security, including Agent Bill of Materials (BOM) generation and prompt-to-tool risk detection. We implement AgentFlow for five representative agent frameworks and evaluate it on AgentZoo, a corpus of 5,399 real-world agent programs. Our evaluation shows that AgentFlow recovers richer agent entities and dependencies than existing AST-based agent static analysis tools, generates more dependency-aware Agent BOMs, and uncovers 238 taint-style prompt-to-tool risks in real-world agent programs. These results show that ADG provides a practical foundation for understanding, governing, and securing emerging agent software.

Generating structured artifacts with Large Language Models - e.g.\ database queries, threat framework mappings, entity schemas - is relatively straightforward; however, making them reliable enough for production deployments presents challenges. We present TAG, a lightweight framework based on a core principle: LLMs generate, we validate. This reframing shifts responsibility from generation quality to validation rigor. The framework rests on three key attributes: First, test driven generation: when tests fail, the LLM receives indicative error messages that expose why the output failed, enabling the LLM to understand its mistakes and refine subsequent attempts. Second, deterministic and LLM-based tests: deterministic tests catch heuristics that can be programmatically verified (schema, syntax, cross-reference), while LLM-based tests evaluate nuanced semantic and delicate features that resist programmatic inspection (intent alignment, logical consistency, domain correctness). Third, expert-distilled judges: LLM-based tests are calibrated to distill and replicate human expert decision distribution, transforming manual human quality gates into scalable, reusable evaluation proxies that reflect professional-grade validation standards. We demonstrate the framework on three artifact types in the security domain - KQL query generation, MITRE ATT&CK mapping, and entity mapping - deployed in production at Microsoft Sentinel. We believe this framework can be applied beyond security to other artifact generation tasks, providing a path to reliable, high-quality outputs without sacrificing the efficiency gains of LLM generation.

Vulnerabilities inherent to the fabless semiconductor manufacturing model have significantly increased the risk of malicious Hardware Trojan (HT) insertion, posing severe threats to hardware security. Several HT mitigation and detection strategies have been developed, and existing works explore the insertion of HTs in the space between standard cells in an integrated circuit. However, there is a lack of research into the vulnerabilities posed by the building blocks of most digital designs on the market today, the standard cells. This work investigates a novel threat model in which standard cells are considered untrusted. Our proposed threat model provides the design house with a tampered standard cell library. The intended netlist is synthesized and implemented using the tampered library. During fabrication, a nefarious foundry replaces the library's deactivated HT cells with activated counterparts. Using open-source and industry-standard Electronic Design Automation (EDA) tools, existing standard cell libraries, Saed32nm and Sky130nm, are converted into malicious libraries capable of masking the presence of arbitrary HTs from IC designers. The malicious library is then applied and characterized in multiple standard benchmark designs. To demonstrate the efficacy and stealthiness of this standard cell-based attack vector, three benchmark circuits, an AES-128 encryption core, an Ethernet controller, and a WISHBONE DMA engine, were synthesized using both clean and Trojan-infected libraries across Synopsys 32nm and SkyWater 130nm technologies. Design-level features, including total cell count, total area, dynamic power consumption, and static power, were extracted from these synthesized circuits to serve as inputs for binary classification

Large Vision-Language Models (LVLMs) have been increasingly integrated into robotic systems. However, these models may exhibit overthinking behaviors, where they generate excessively long reasoning traces, incurring an excessive inference time. This overthinking behavior poses a serious risk to robotic systems, as the adversary can deliberately trigger overthinking to slow down the decision making of a victim robotic system, causing a variety of safety issues (i.e., an overthinking-induced slowdown attack). To initiate this attack, an adversary can embed carefully crafted, human-readable scene text into the visual scene observed by a victim robotic agent, causing significant inference delays even under a strict black-box setting. Therefore, the embedded scene text serves as a significant "trigger" for the attack. This work systematically identifies and validates transferable triggers of overthinking in robotic systems by introducing a three-stage framework. First, we construct a diverse corpus of reasoning-intensive scene text and extract overthinking-correlated lexical features from short response prefixes. Second, we perform an efficient black-box search guided by a prefix-based proxy score while selectively confirming a small set of top candidates with full latency measurements. Third, we evaluate black-box transfer using a fixed pool of triggers on unseen images and multiple LVLMs, reporting latency amplification and attack success rates under standard thresholds. Across three representative LVLMs, all triggers yield slowdown ratios greater than 1.0x, with the strongest single-trigger case reaching 6.96x. The physical printing of the text trigger still causes up to 4.74x latency amplification. These results demonstrate that our discovered triggers are transferred between multiple LVLM models and consistently cause significant slowdowns in robotic systems.

AI agents that autonomously execute tool calls on a user's behalf raise pressing questions about permission management: what role could users play, and what role should they play? Despite many proposed approaches, the user's role in agentic permission management remains underexplored. We introduce Janus, a playground system for implementing and evaluating user-involved agentic permission management designs. Janus consists of two components: Janus-Core, a modular agentic system supporting a diverse spectrum of permission management designs, and Janus-Harness, an automated evaluation framework. Grounded in a conceptual model that identifies key design axes for user involvement, we implement six permission assistants spanning the design space and evaluate them across three scenarios with four subscenarios each and three synthetic responders. We demonstrate that user involvement is critical and can strengthen privacy and security and that user behavior such as permission fatigue must be accounted for in system design. No single design performs optimally across all contexts, motivating a more principled and context-sensitive approach to deploying permission assistants in agentic systems. Janus is publicly available to support future investigation into this dimension of agentic system design.

Recent work has established a fundamental trilemma between Byzantine robustness, local differential privacy (LDP), and optimization error in distributed learning. We show that this trilemma does not universally extend to generalization error, but instead depends critically on the privacy regime. Specifically, in the high-noise regime (strong privacy), we prove that increasing privacy reduces the generalization error, i.e., there is no tension between robustness and privacy. In the low-noise regime (weaker privacy), however, the tension between robustness and privacy reappears and increasing privacy indeed degrades generalization. Our theory explains this surprising non-monotonic behavior of the generalization error via matching lower and upper bounds on the algorithmic stability of Byzantine-robust distributed learning under LDP constraints. We corroborate and further analyze these theoretical findings with empirical evaluations.

Malware poses a critical and ever-evolving threat, and robust and effective systems for detecting and classifying malware are of essential importance. $n$-grams features are among the common static features used in effective machine learning systems for malware, but these features are inherently brittle. We propose an algorithm for constructing more robust features, hamm-grams, which are a special class of regular expressions having a fixed length and single-character wildcards. We devise an efficient algorithm for finding common hamm-grams using a new locality-sensitive hash designed to produce collisions among pairs of small Hamming distance and a clustering within hash buckets to place wildcards. We then demonstrate the advantages of these features in malware classification and detection tasks.

Identity document forgery has undergone a fundamental capability shift: generative AI tools now enable high-fidelity document synthesis and field-level manipulation with minimal technical expertise, while detection methods remain constrained by benchmarks that do not reflect this threat. The resulting attack surface spans physical presentation, digital injection, and fully generative synthesis, introducing distinct forensic failure modes that require a unified threat model and evaluation framework. This survey provides, to our knowledge, the first unified treatment of Presentation Attacks, Digital Injection Attacks, and GenAI-driven synthesis within a single identity verification threat model. We trace detection methodologies from rule-based heuristics through forensic localisation, injection-aware pipelines, foundation models, and few-shot frameworks. A systematic audit of public datasets from 2019–2025 exposes a persistent Reality Gap between benchmark conditions and operational deployment. We further analyse large multimodal models for identity document manipulation, identifying Script-Dependent Generative Instability (SDGI) as a recurring typographic failure mode in non-Latin script inpainting. Finally, zero-shot benchmarking on unseen synthesised ID cards shows that even the strongest publicly available models achieve APCER values above 25% under security-oriented operating conditions, highlighting substantial limits in cross-domain generalisation. We conclude by outlining future directions toward forensically grounded, privacy-preserving, and legally accountable identity verification systems.

Significant advancement of immersive technologies such as Virtual and Augmented Reality (VR/AR) and their integration into diverse aspects of modern life need authentication interfaces that are secure, intuitive, and compatible with embodied interaction. Traditional methods such as passwords, PINs, and device-based logins, break immersion and rely on external hardware. Recent 3D-specific behavioral approaches, such as hand-gesture, eye-tracking, and electroencephalography (EEG)-based methods, offer promising alternatives but often require specialized sensors or constrain natural movement, limiting usability in dynamic environments. We present Sign in the Air to Unlock, an in-air signature interface that enables users to authenticate by signing naturally in 3D space which is a familiar, personal, and reproducible gesture. To realize this interface, we design a point-voxel Cross-Attention Network (PV-Net) that jointly models local motion dynamics and global spatial structure from 3D trajectories. The model is evaluated on two datasets: the public DeepAirSig dataset (1,800 signatures from 40 users) and ImmAirsig, a new dataset collected using Meta Quest 2 in immersive VR (880 samples from 22 users). PV-Net achieves an Equal Error Rate of 2.5% on DeepAirSig and 76% classification accuracy on ImmAirSig. These findings highlight the potential of 3D behavioral interfaces for seamless, user-centric authentication that merges security with natural interaction in immersive environments.