{"total":25,"rows":[{"id":"2512.15699","title":"FrontierCS: Evolving Challenges for Evolving Intelligence","created":"2025-12-17","cited_by_count":23,"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":"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":"2606.14295","title":"AgentCyberRange: Benchmarking Frontier AI Systems in Realistic Cyber Ranges","created":"2026-06-12","cited_by_count":4,"area":null},{"id":"2605.12233","title":"No More, No Less: Task Alignment in Terminal Agents","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2512.02625","title":"CryptoQA: A Large-scale Question-answering Dataset for AI-assisted Cryptography","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2605.29963","title":"Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2608.03070","title":"AI Security Leaderboard: Methodology, Results and Minimal Standard","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2508.15808","title":"Uplifted Attackers, Human Defenders: The Cyber Offense-Defense Balance for Trailing-Edge Organizations","created":"2025-08-14","cited_by_count":0,"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":"2605.11029","title":"FragBench: Cross-Session Attacks Hidden in Benign-Looking Fragments","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.20896","title":"GenAI-Driven Threat Detection with Microsoft Security Copilot","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.22568","title":"Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2607.00913","title":"Two AI Metrics Diverged: Will it Make All the Difference?","created":"2026-07-01","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":"2607.16112","title":"Harmonizing AI Safety Thresholds","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2608.15012","title":"SysEvolve: An AI-native, safe, autonomous adversarial attack-defense co-evolutionary system","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2608.25158","title":"FuzzingBrain-Bench V1: Evaluating Open-Ended Bug Discovery by LLMs","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.00578","title":"Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversational Contexts","created":"2026-09-01","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":"2609.08418","title":"Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.23889","title":"SyzHarness: Patch-Based Kernel Bug Reproduction with LLM-Synthesized Fuzzing Harnesses","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.38954","title":"APTInvestBench: Evaluating Autonomous APT Investigation under Varying Telemetry","created":"2026-09-30","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}