DIBench: Benchmarking Decision Integrity of GUI-based Mobile Agents Under...
arXiv:2610.06898v1 Announce Type: new Abstract: As GUI-based mobile agents rapidly progress, rigorous safety evaluation of their autonomous decision-making in realistic app interfaces becomes...
View ArticleAPEX: Active Protection at Execution Boundaries for LLM Agents
arXiv:2610.06966v1 Announce Type: new Abstract: Indirect prompt injection (IPI) hides adversarial instructions in content that large language model (LLM) agents read at runtime. As agents compose...
View ArticleTARE: Weigh a Never-Poisoned Twin Before Reading Backdoor-Defense Costs
arXiv:2610.06994v1 Announce Type: new Abstract: Backdoor-defense leaderboards print a clean-accuracy drop and read it as removal cost. Measured on the poisoned victim alone, the drop cannot separate...
View ArticleWhich Image Property Carries the Jailbreak? A Controlled Dissection of...
arXiv:2610.07009v1 Announce Type: new Abstract: Image-to-text jailbreaks place harmful intent in text, image content, or the relationship between them. We examine image-side factors across four...
View ArticleTowards a Unified Misuse Monitoring Benchmark
arXiv:2610.07089v1 Announce Type: new Abstract: LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition attacks, where a harmful request is...
View ArticleJailbreaking Open-Weight LLMs via Random Embedding Perturbations
arXiv:2610.07125v1 Announce Type: new Abstract: While open-weight models have enjoyed steady progress in capabilities and wide adoption across multiple domains, their safety remains an important...
View ArticleEfficient Auditing of Adversarial AI Agent Behavior from Agent Traces
arXiv:2610.07256v1 Announce Type: new Abstract: AI agents powered by large language models (LLMs) can perform complex tasks but may harm the systems they operate in, either intentionally or...
View ArticleLineage-Aware Memory Governance: A Derivation-Gated Framework for...
arXiv:2610.07258v1 Announce Type: new Abstract: Enterprise AI agents that share a memory store face two unaddressed risks: sensitive data can leak through legitimately computed results the requester...
View ArticleA Resilient Runtime-Verification Fabric for Security Monitoring of Critical...
arXiv:2610.07282v1 Announce Type: new Abstract: Protecting critical infrastructure increasingly depends on continuously verifying large IoT fleets against formal security specifications at runtime. Yet...
View ArticlePolar: LLM-Powered Synthesis of Real-World Cyber Evidence for Prioritization...
arXiv:2610.07298v1 Announce Type: new Abstract: Cyber threat analysis increasingly depends on evidence distributed across vendor advisories, vulnerability databases, and threat intelligence sources....
View ArticleFrom Sandbox to Enforcement: Confidence-Qualified Threat Intelligence for...
arXiv:2610.07310v1 Announce Type: new Abstract: Security operations centres and national incident-response teams defending critical infrastructure collect abundant threat data yet struggle to turn it...
View ArticleEvaluating Behavioral Context for Interpretable IAM Policy Risk Scoring in...
arXiv:2610.07345v1 Announce Type: new Abstract: IAM policy analysis typically emphasizes the authorization capabilities encoded in a policy, but security analyst review priority may also depend on the...
View ArticleSimple Extremely Lossy Functions from Small-Exponent Hashing
arXiv:2610.07351v1 Announce Type: new Abstract: Extremely Lossy Functions (ELFs) are a standard model primitive that captures many useful properties of random oracles (Zhandry, Crypto 2016). While...
View ArticleNetAgent: Multi-Task Agentic Network Traffic Analysis Made Practical
arXiv:2610.07386v1 Announce Type: new Abstract: Network traffic analysis is central to network security, spanning tasks from intrusion detection to encrypted traffic classification. Existing approaches...
View ArticleDeep Defence on Wheels: A Dual Intrusion Detection System Architecture for...
arXiv:2610.07489v1 Announce Type: new Abstract: Increasing connectivity to the outside world and the lack of inbuilt security mechanisms have made legacy intra-vehicular networks vulnerable to...
View ArticleUnderstanding and Enhancing Backdoor Persistency in LLM Agent Post-Training
arXiv:2610.07510v1 Announce Type: new Abstract: Developers can build LLM agents by adapting third-party models through benign post-training. We study a supply-chain threat in which an attacker supplies...
View ArticleBVI: Lightweight, Data-Centric Blockchain-Based Verification of Identity Claims
arXiv:2610.07531v1 Announce Type: new Abstract: A person who answers an unexpected call claiming to come from a bank has no way to check the claim. Australian text messaging has labelled a message as...
View ArticleSafeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge
arXiv:2610.07532v1 Announce Type: new Abstract: LLMs have advanced rapidly, raising growing concerns about their safety. Recent work has proposed approaches to detect and defend against attacks...
View ArticleCISB-Bench: An Auditable Source--IR Dataset of Compiler-Introduced Security Bugs
arXiv:2610.07635v1 Announce Type: new Abstract: Compiler-introduced security bugs (CISBs) arise when an optimization, lowering, or instrumentation decision changes a security-relevant property of the...
View ArticleHarnessSecurity-Bench: Do Security Mechanisms Really Protect Coding Agent...
arXiv:2610.07639v1 Announce Type: new Abstract: Coding agent harnesses mediate tool use and authorize actions, yet their security mechanisms and runtime effects remain incompletely characterized. We...
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)
