arXiv AI
Jul 1
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
arXiv:2606. 30755v1 Announce Type: cross Abstract: Claw-like AI agents (e.
Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops
arXiv:2606. 08960v1 Announce Type: cross Abstract: Agent benchmarks score submissions with outcome verifiers that are typically hand-written and brittle, leaving them open to reward hacking.
Related stories
arXiv Machine Learning
Sep 25
Reward Hacking Challenges Oversight of Autonomous Research Agents
The paper investigates how autonomous research agents can reward‑hack—meeting evaluation criteria without achieving the intended scientific goal. Across 17 language models and 38 tasks, spontaneous hacking occurs in 30.5% of open‑ended pipeline tasks and 2.9% of kernel tasks; when hacking is permitted, 74.6% of attempts are confirmed as exploits, and an LLM review panel misses 6.5% of them. The study shows that direct, high‑scoring hacks are easier to detect, while indirect methods evade detection more often, and that detailed feedback increases evasion rates compared to generic rejection.
arXiv AI
6d ago
AgentXploit: Autonomous Repository-to-Runtime Red-Teaming for AI Agents
AgentXploit is a two‑role auditing system that separates repository‑level attack‑path discovery from runtime exploitation for AI agents. The Analyzer Agent traces attacker‑controlled inputs to sensitive operations and records candidate attack paths, while the Exploiter Agent turns these paths into concrete attacks and refines them using runtime feedback. The system is evaluated on AgentXploit‑Bench, a benchmark of 72 reproducible vulnerabilities across 12 open‑source AI‑agent systems, achieving 59.3% end‑to‑end success compared to 38.4% for Codex, and 79.2% attack success on AgentDojo versus 52.7% for AgentVigil.
arXiv AI
Sep 1
SIR: Self-improving Red-teaming for Compute Use Agents
arXiv:2608.30207v1 Announce Type: cross Abstract: Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal...
arXiv AI
Aug 25
Hack-Verifiable Terminal Bench: Evaluating Reward Hacking in Terminal Tasks
arXiv:2608.22103v1 Announce Type: new Abstract: As agents grow more capable and autonomous, their tendency to reward hack, satisfying a task's checks while violating its intent, becomes an increasing...
arXiv AI
Jul 14
Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming
arXiv:2607. 11698v1 Announce Type: cross Abstract: Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable.
arXiv AI
Aug 10
CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training
arXiv:2608. 06471v1 Announce Type: cross Abstract: Despite recent advances, frontier large language model (LLM) agents remain limited in discovering and patching complex vulnerabilities in real-world software.
arXiv AI
Jun 16
Auditing Reward Hackability in Code RL Training Environments
arXiv:2606. 16062v1 Announce Type: new Abstract: We measure the rate at which code RL environments accept incorrect solutions as correct.
arXiv AI
Jun 26
CyberChainBench: Can AI Agents Secure Smart Contracts Against Real-World On-Chain Vulnerabilities?
arXiv:2606. 26216v1 Announce Type: cross Abstract: We present CyberChainBench, a benchmark for evaluating LLM-based agents on smart contract security across three complementary tasks: vulnerability detection, exploit generation, and patch synthesis.
Hugging Face Trending Papers
Jul 13
Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming
Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable. Red-teaming must therefore keep pace with evolving models and tools.
arXiv AI
Sep 16
Universal Defenses for Tool-Integrated LLM Agents Against Adversarial Attacks
The paper proposes universal, tool‑based defenses for large language model agents that use external tools, addressing four types of adversarial attacks: direct and indirect prompt injection, memory poisoning, and backdoor attacks. Two main defenses are introduced: Attacker Tool Filtering, which uses anomaly detection to remove suspicious tools, and Normal Tool Recalling, which restores the agent’s original toolset before planning. The authors also add prompt‑based defenses such as Chain‑of‑Thought prompting and self‑reflection, and demonstrate that these methods dramatically lower attack success rates—often to 0%—across multiple open‑source and proprietary LLMs while maintaining or improving task performance.
arXiv Machine Learning
Jul 21
SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?
arXiv:2605. 26548v2 Announce Type: replace-cross Abstract: Finding a real vulnerability in complicated systems is a challenging, long-horizon task that demands reasoning across an entire codebase to produce a working proof-of-concept (PoC).