{"total":17,"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":"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":"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":"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":"2603.04915","title":"EVMbench: Evaluating AI Agents on Smart Contract Security","created":"2026-03-05","cited_by_count":7,"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":"2603.17974","title":"Toward Scalable Automated Repository-Level Datasets for Software Vulnerability Detection","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2606.13892","title":"Crypto x AI, AI x Crypto: A Survey","created":"2026-06-11","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":"2609.30325","title":"ScopeBench: Do Agents Preserve Engagement Boundaries Under Goal Pressure?","created":"2026-09-23","cited_by_count":1,"area":null},{"id":"2602.08889","title":"Scalable Delphi: Large Language Models for Structured Risk Estimation","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2606.15123","title":"Data-Centric Benchmarking of Exploit Generation in LLMs: Understanding the Impact of Fine-Tuning","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2607.27030","title":"HoF-Bench: Rediscovering Real AI-Discovered CVEs Without Frontier Models","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.06229","title":"SWE-Test: Benchmarking LLM Vulnerability Discovery via Input Prediction","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.15383","title":"Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2610.06584","title":"Does AI Help Cyber Attackers or Defenders? Evidence from Nonpublic Vulnerabilities and Subsequent Attacks","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}