{"total":32,"rows":[{"id":"2506.02548","title":"CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale","created":"2025-06-03","cited_by_count":78,"area":null},{"id":"2502.11844","title":"BaxBench: Can LLMs Generate Correct and Secure Backends?","created":"2025-02-17","cited_by_count":41,"area":null},{"id":"2503.17354","title":"HCAST: Human-Calibrated Autonomy Software Tasks","created":"2025-03-21","cited_by_count":24,"area":null},{"id":"2504.05408","title":"Frontier AI's Impact on the Cybersecurity Landscape","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2603.02277","title":"Quantifying Frontier LLM Capabilities for Container Sandbox Escape","created":"2026-03-01","cited_by_count":18,"area":null},{"id":"2503.11917","title":"A Framework for Evaluating Emerging Cyberattack Capabilities of AI","created":"2025-03-14","cited_by_count":16,"area":null},{"id":"2503.01811","title":"AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses","created":"2025-03-03","cited_by_count":15,"area":null},{"id":"2512.09882","title":"Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing","created":"2025-12-10","cited_by_count":15,"area":null},{"id":"2504.10112","title":"Benchmarking Practices in LLM-driven Offensive Security: Testbeds, Metrics, and Experiment Design","created":"2025-04-14","cited_by_count":14,"area":null},{"id":"2605.26548","title":"SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?","created":"2026-05-26","cited_by_count":9,"area":null},{"id":"2411.01236","title":"AutoPT: How Far Are We from the End2End Automated Web Penetration Testing?","created":"2024-11-02","cited_by_count":8,"area":null},{"id":"2606.04460","title":"CyberGym-E2E: Scalable Real-World Benchmark for AI Agents' End-to-End Cybersecurity Capabilities","created":"2026-06-03","cited_by_count":8,"area":null},{"id":"2510.11688","title":"PACEbench: A Framework for Evaluating Practical AI Cyber-Exploitation Capabilities","created":"2025-10-13","cited_by_count":7,"area":null},{"id":"2407.08708","title":"eyeballvul: a future-proof benchmark for vulnerability detection in the wild","created":"2024-07-11","cited_by_count":6,"area":null},{"id":"2505.19395","title":"VADER: A Human-Evaluated Benchmark for Vulnerability Assessment, Detection, Explanation, and Remediation","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2410.11096","title":"SeCodePLT: A Unified Platform for Evaluating the Security of Code GenAI","created":"2024-10-14","cited_by_count":4,"area":null},{"id":"2606.14295","title":"AgentCyberRange: Benchmarking Frontier AI Systems in Realistic Cyber Ranges","created":"2026-06-12","cited_by_count":4,"area":null},{"id":"2505.12938","title":"Leveraging LLM Inconsistency to Boost Pass@k Performance","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2507.19399","title":"Running in CIRCLE? A Simple Benchmark for LLM Code Interpreter Security","created":"2025-07-25","cited_by_count":2,"area":null},{"id":"2509.06921","title":"Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2606.10281","title":"Benchmarking and Exploring the Capabilities of LLMs for Attack Investigations","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2410.18312","title":"Countering Autonomous Cyber Threats","created":"2024-10-23","cited_by_count":1,"area":null},{"id":"2601.22159","title":"RedSage: A Cybersecurity Generalist LLM","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2604.06019","title":"CritBench: A Framework for Evaluating Cybersecurity Capabilities of Large Language Models in IEC 61850 Digital Substation Environments","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2604.20389","title":"CyberCertBench: Evaluating LLMs in Cybersecurity Certification Knowledge","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2607.15263","title":"Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2605.23243","title":"Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.29115","title":"unix-ctf: Procedural Environments for Unix-Competence Reinforcement Learning","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.01764","title":"Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.25425","title":"The Disruptive Impact of Large Language Models on Capture the Flag Competitions and the Path Toward Fair Play","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.08418","title":"Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.18120","title":"PentestChain: A Cost-Aware, MCP-Orchestrated Framework for Automated Penetration Testing with Free-Tier LLMs","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}