Changkun Ou/Library

ReplicHAI › Agent Evals › 08 Safety & security

Shared by Changkun Ou with everyone

13 entries Export .bib
Year ↓ Title added Authors Venue
Preprint 2026 CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale Wang et al. arXiv
Preprint 2026 KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards Li et al. arXiv
Preprint 2026 The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark Spence et al. arXiv
Preprint 2025 AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents Andriushchenko et al. arXiv
Preprint 2025 BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems Zhang et al. arXiv
Preprint 2025 CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities Zhu et al. arXiv
Preprint 2025 Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models Zhang et al. arXiv
Preprint 2025 NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security Shao et al. arXiv
Preprint 2025 OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents Kuntz et al. arXiv
Preprint 2024 AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents Debenedetti et al. arXiv
Preprint 2024 Identifying the Risks of LM Agents with an LM-Emulated Sandbox Ruan et al. arXiv
Preprint 2024 InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents Zhan et al. arXiv
Preprint 2024 RedCode: Risky Code Execution and Generation Benchmark for Code Agents Guo et al. arXiv

/ filter · j k or ↑ ↓ select · Enter open page · c copy BibTeX