Adversarial RL for Port-Scan Evasion: Attacker Feature Visibility in...
arXiv:2610.08864v1 Announce Type: new Abstract: Machine learning-based intrusion detection systems (IDS) are increasingly used in resource-constrained Internet of Things (IoT) environments, yet their...
View ArticleA Deployment-Aware Feasibility Framework for Machine Learning-Based IoT...
arXiv:2610.08867v1 Announce Type: new Abstract: The rapid growth and heterogeneity of Internet of Things (IoT) environments have exposed fundamental limitations in traditional rule-based and...
View ArticleVisible-Spectrum Optical Covert Channels in Commodity Smart Lighting
arXiv:2610.08868v1 Announce Type: new Abstract: Smart light-emitting diode (LED) bulbs are networked devices that produce information-carrying output. This study asks whether that light can carry...
View ArticleCredLeakBench: Evaluating Credential Leakage and Recovery in LLM Agents
arXiv:2610.08871v1 Announce Type: new Abstract: Language model agents are increasingly deployed to automate everyday digital chores from managing emails and social media to handling banking and bills...
View ArticleTowards Verifying Neural Networks Against Multi-Parameter Bit-Flip Perturbations
arXiv:2610.08876v1 Announce Type: new Abstract: Hardware faults can flip bits in the stored weights of a quantized neural network, potentially compromising its predictions. While such faults typically...
View ArticleContextualization of Third-Party Cloud Security Findings
arXiv:2610.08895v1 Announce Type: new Abstract: Finding severity is the main driver of how security teams prioritize remediation. For third-party cloud security findings, that severity is static: the...
View ArticleMulti-Aspect Runtime Verification for Simulation-Based V&V of LLM-Enabled...
arXiv:2610.08928v1 Announce Type: new Abstract: LLM-based agents are entering decision-support roles in defence staff work, where the obligations they must respect are already written down and binding,...
View ArticleASPIRE: Agentic Safety & Prompt Injection Red-teaming Engine
arXiv:2610.08951v1 Announce Type: new Abstract: LLM agents retrieve untrusted content and act through tools, creating indirect prompt-injection risks that can cause unauthorized actions or persistent...
View ArticleTwinGuard-Lite: A Rule-Based State-Admission Gateway for Generative Patient...
arXiv:2610.09012v1 Announce Type: new Abstract: Future generative patient digital twins may combine longitudinal health records with language-model agents and keep information across sessions. The...
View ArticleVisual Memory Attacks Can Persist Through The KV Cache
arXiv:2610.09027v1 Announce Type: new Abstract: Modern language model systems operate autonomously over increasingly long contexts containing untrusted text and images. Can an adversarial input...
View ArticleCost of Delay for Post-Quantum Migration: Putting Classical and...
arXiv:2610.09029v1 Announce Type: new Abstract: Organisations deciding which assets to migrate to post-quantum cryptography first, and how that work competes with a backlog of classical findings, lack...
View ArticleSwarmReconGuard: Black-Box Detection of Distributed Collective Reconnaissance...
arXiv:2610.09138v1 Announce Type: new Abstract: Autonomous and agentic clients can distribute reconnaissance across many identities so that each request remains valid, low-rate, and benign-looking...
View ArticleAdversarial Images Hijack Web Agents from Visual Grounding to Browser Execution
arXiv:2610.09240v1 Announce Type: new Abstract: Modern web agents built on large vision-language models process webpages, select relevant UI elements, and translate model outputs into browser actions....
View ArticlePackage Hallucination Attacks on Coding Agents through Prompt Injection in...
arXiv:2610.09264v1 Announce Type: new Abstract: Modern agentic coding frameworks increasingly rely on community-shared rule files (e.g., AGENTS.md or .cursorrules) to guide autonomous code generation,...
View ArticleAsk the Expert: LLM-Guided Reinforcement Learning for Autonomous Cyber Defense
arXiv:2610.09337v1 Announce Type: new Abstract: Policy-based reinforcement learning (RL) approaches have produced promising results for autonomous cyber defense; however, they are sample-inefficient in...
View ArticleSecure-CUA: Controlling Untrusted Influence in Computer-Use Agents
arXiv:2610.09469v1 Announce Type: new Abstract: Computer-use agents (CUAs) perform tasks across applications (such as desktops, mobile apps, and web browsers) by observing graphical interfaces and...
View ArticleConstitution-Guided Watermarking
arXiv:2610.09552v1 Announce Type: new Abstract: Watermarking enables language model providers to identify text generated by their models. However, its desired properties can conflict (\ie~stronger...
View ArticleMARS: Malware Analysis with Rule-Based Scoring of LLM Claims
arXiv:2610.09553v1 Announce Type: new Abstract: Large language models can triage malware through direct verdicts or behavioral claims scored by an external policy. We present MARS, a malware triage...
View ArticleCorrect Answers, Unsupported Findings: Evidence Binding in Forensic...
arXiv:2610.09581v1 Announce Type: new Abstract: Forensic reconstruction of LLM-agent actions requires not only recovering the correct value, but establishing which preserved record supports that...
View ArticleAutomotive Hardware Attacks: An Architect's Guide to TARA
arXiv:2610.09697v1 Announce Type: new Abstract: Threat analysis and risk assessment (TARA) according to ISO/SAE 21434 treats implementation-level hardware attacks inconsistently. We show that two of...
View Article
![[TVRIP] Vertex Force [バーテックスフォース] 第01話](http://animerss.com/img/TVRIP-Vertex-Force.jpg)
