Package Hallucination Attacks on Coding Agents through Prompt Injection in Rule Files
Modern agentic coding frameworks increasingly rely on community-shared rule files (e.g., AGENTS.md or .cursorrules) to g
#cs.AI
共收录 1652 条相关情报。
← 返回所有主题Adversarial Images Hijack Web Agents from Visual Grounding to Browser Execution
Modern web agents built on large vision-language models process webpages, select relevant UI elements, and translate mod
SwarmReconGuard: Black-Box Detection of Distributed Collective Reconnaissance by Individually Benign-Looking Agent Populations
Autonomous and agentic clients can distribute reconnaissance across many identities so that each request remains valid,
Certified Corruption Budgets: Anytime-Valid Leaderboard Claims under Adaptive Rigging
Public leaderboards for AI models are read continuously, and attackers can see every published standing. Vote rigging, s
Quad-State Safety Evaluation of Open-Weight Large Language Models on Non-Canonical Inputs
Standard safety evaluations of large language models assess harmful requests written in canonical plain text, while mode
Visual Memory Attacks Can Persist Through The KV Cache
Modern language model systems operate autonomously over increasingly long contexts containing untrusted text and images.
Sigma-Hunter: A Domain-Specific Language Model for Threat Hunting and Detection Engineering
Detection engineers must translate threat reports, forensic observations, and hunt hypotheses into precise, testable rul
How Fragile Is On-Device Language Model Safety? Localizing Safety-Critical Parameters for Sparse Fault Analysis
As small language models (SLMs) are increasingly deployed on resource-constrained and on-device platforms, including as
Multi-Aspect Runtime Verification for Simulation-Based V&V of LLM-Enabled Autonomous Agents
LLM-based agents are entering decision-support roles in defence staff work, where the obligations they must respect are
Secure Speculative Decoding for Large Language Models
Speculative decoding accelerates inference for a large language model (LLM), referred to as the \emph{target model}, by
Semantic Behavioral Watermarking: Paraphrase-Robust and Forgery-Resistant Provenance for LLM Agents
Behavioral watermarking embeds an owner identifier in an LLM agent's high-level action choices, giving provenance withou
Contextualization of Third-Party Cloud Security Findings
Finding severity is the main driver of how security teams prioritize remediation. For third-party cloud security finding
RAG-PIBench: A Leakage-Aware Benchmark for Prompt-Injection Detection in Trustworthy RAG Systems
Retrieval-Augmented Generation (RAG) systems are vulnerable to prompt-injection attacks embedded in retrieved content. W
Learning from Failures: A Failure-Driven Prompt Refinement for LLM-Based Vulnerability Analysis
Large Language Models have emerged as promising tools for software vulnerability analysis, but their effectiveness depen
MARCO: The Radioactive Watermark for Protein Generative Models
Protein Generative Models (PGMs) have revolutionized structural biology by enabling the design of complex 3D protein str
When Tools Lie: Reliability of Mathematical Agents Under Corrupted Tool Feedback
Mathematical problem solving often requires deterministic computational steps that agents delegate to tools and implicit
CredLeakBench: Evaluating Credential Leakage and Recovery in LLM Agents
Language model agents are increasingly deployed to automate everyday digital chores from managing emails and social medi
Where Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems Security
LLM-based multi-agent systems (MAS) engage tools, share memory, and delegate tasks, often encountering adversarial conte
SkillPoison: Progressive Skill Poisoning via Successful Experiences
Self-improving LLM agents increasingly distill successful experiences into persistent, reusable skills. Existing skill a
CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?
Static-analysis checker synthesis requires agents to interpret a defect specification, inspect a repository, implement a