{"total":138,"rows":[{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429,"area":"safety"},{"id":"2501.14249","title":"Humanity's Last Exam","created":"2025-01-24","cited_by_count":491,"area":null},{"id":"2401.10019","title":"R-Judge: Benchmarking Safety Risk Awareness for LLM Agents","created":"2024-01-18","cited_by_count":288,"area":"agents"},{"id":"2404.07921","title":"AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs","created":"2024-04-11","cited_by_count":172,"area":"safety"},{"id":"2402.09283","title":"Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey","created":"2024-02-14","cited_by_count":130,"area":null},{"id":"2401.18018","title":"On Prompt-Driven Safeguarding for Large Language Models","created":"2024-01-31","cited_by_count":116,"area":"safety"},{"id":"2411.07781","title":"RedCode: Risky Code Execution and Generation Benchmark for Code Agents","created":"2024-11-12","cited_by_count":90,"area":"agents"},{"id":"2404.13161","title":"CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models","created":"2024-04-19","cited_by_count":89,"area":"safety"},{"id":"2401.13138","title":"Visibility into AI Agents","created":"2024-01-23","cited_by_count":79,"area":null},{"id":"2404.05399","title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","created":"2024-04-08","cited_by_count":77,"area":"safety"},{"id":"2405.03644","title":"When LLMs Meet Cybersecurity: A Systematic Literature Review","created":"2024-05-06","cited_by_count":71,"area":null},{"id":"2406.07599","title":"CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligence","created":"2024-06-11","cited_by_count":62,"area":null},{"id":"2410.21965","title":"SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types","created":"2024-10-29","cited_by_count":60,"area":"safety"},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"id":"2501.08200","title":"CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation","created":"2025-01-14","cited_by_count":59,"area":null},{"id":"2408.01605","title":"CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models","created":"2024-08-02","cited_by_count":58,"area":null},{"id":"2403.09032","title":"CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences","created":"2024-03-14","cited_by_count":57,"area":"alignment"},{"id":"2409.16165","title":"EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities","created":"2024-09-24","cited_by_count":52,"area":"agents"},{"id":"2410.21514","title":"Sabotage Evaluations for Frontier Models","created":"2024-10-28","cited_by_count":52,"area":null},{"id":"2604.20779","title":"SWE-chat: Coding Agent Interactions From Real Users in the Wild","created":"2026-04-22","cited_by_count":43,"area":"agents"},{"id":"2501.10114","title":"Infrastructure for AI Agents","created":"2025-01-17","cited_by_count":41,"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":"2405.00218","title":"Constrained Decoding for Secure Code Generation","created":"2024-04-30","cited_by_count":37,"area":null},{"id":"2601.17548","title":"Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems","created":"2026-01-24","cited_by_count":31,"area":"agents"},{"id":"2407.02395","title":"Toward Secure Code Generation: Bridging Correctness and Security via Task-Adaptive Vulnerability Modeling and Execution-Based Benchmarking","created":"2024-07-02","cited_by_count":27,"area":null},{"id":"2504.09420","title":"SaRO: Enhancing LLM Safety through Reasoning-based Alignment","created":"2025-04-13","cited_by_count":26,"area":"lr"},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"id":"2411.12882","title":"ProSec: Fortifying Code LLMs with Proactive Security Alignment","created":"2024-11-19","cited_by_count":25,"area":"alignment"},{"id":"2412.03578","title":"PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback","created":"2024-11-18","cited_by_count":24,"area":null},{"id":"2408.08333","title":"CodeMirage: Hallucinations in Code Generated by Large Language Models","created":"2024-08-14","cited_by_count":23,"area":null},{"id":"2501.07238","title":"Lessons From Red Teaming 100 Generative AI Products","created":"2025-01-13","cited_by_count":23,"area":"safety"},{"id":"2410.10343","title":"Locking Down the Finetuned LLMs Safety","created":"2024-10-14","cited_by_count":22,"area":null},{"id":"2508.00910","title":"Cyber-Zero: Training Cybersecurity Agents without Runtime","created":"2025-07-29","cited_by_count":22,"area":"agents"},{"id":"2407.12858","title":"Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)","created":"2024-07-10","cited_by_count":20,"area":null},{"id":"2410.03837","title":"Learning Code Preference via Synthetic Evolution","created":"2024-10-04","cited_by_count":19,"area":null},{"id":"2409.06446","title":"HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data","created":"2024-09-10","cited_by_count":16,"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":"2508.18370","title":"Training Language Model Agents to Find Vulnerabilities with CTF-Dojo","created":"2025-08-25","cited_by_count":15,"area":"agents"},{"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":"2504.21205","title":"SecRepoBench: Benchmarking Code Agents for Secure Code Completion in Real-World Repositories","created":"2025-04-29","cited_by_count":14,"area":"agents"},{"id":"2508.18106","title":"A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code","created":"2025-08-25","cited_by_count":14,"area":null},{"id":"2603.11214","title":"Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios","created":"2026-03-11","cited_by_count":14,"area":"agents"},{"id":"2509.22097","title":"SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios","created":"2025-09-26","cited_by_count":13,"area":"agents"},{"id":"2502.06039","title":"Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models","created":"2025-02-09","cited_by_count":12,"area":"lr"},{"id":"2502.15797","title":"OCCULT: Evaluating Large Language Models for Offensive Cyber Operation Capabilities","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2505.22704","title":"Training Language Models to Generate Quality Code with Program Analysis Feedback","created":"2025-05-28","cited_by_count":12,"area":null},{"id":"2410.06809","title":"Root Defence Strategies: Ensuring Safety of LLM at the Decoding Level","created":"2024-10-09","cited_by_count":11,"area":"safety"},{"id":"2509.07604","title":"K2-Think: A Parameter-Efficient Reasoning System","created":"2025-09-09","cited_by_count":11,"area":"lr"},{"id":"2407.11733","title":"How Are LLMs Mitigating Stereotyping Harms? Learning from Search Engine Studies","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2410.16527","title":"Insights and Current Gaps in Open-Source LLM Vulnerability Scanners: A Comparative Analysis","created":"2024-10-21","cited_by_count":10,"area":"safety"},{"id":"2504.00018","title":"SandboxEval: Towards Securing Test Environment for Untrusted Code","created":"2025-03-27","cited_by_count":10,"area":null},{"id":"2502.02009","title":"LLMSecConfig: An LLM-Based Approach for Fixing Software Container Misconfigurations","created":"2025-02-04","cited_by_count":9,"area":null},{"id":"2510.02609","title":"RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents","created":"2025-10-02","cited_by_count":9,"area":"agents"},{"id":"2404.09785","title":"Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations","created":"2024-04-15","cited_by_count":8,"area":null},{"id":"2407.02518","title":"INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness","created":"2024-06-23","cited_by_count":8,"area":null},{"id":"2408.09326","title":"Characterizing and Evaluating the Reliability of LLMs against Jailbreak Attacks","created":"2024-08-18","cited_by_count":8,"area":"safety"},{"id":"2409.15361","title":"Multitask Mayhem: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuning","created":"2024-09-18","cited_by_count":8,"area":"safety"},{"id":"2505.18384","title":"Dynamic Risk Assessments for Offensive Cybersecurity Agents","created":"2025-05-23","cited_by_count":8,"area":"agents"},{"id":"2601.00477","title":"Security in the Age of AI Teammates: An Empirical Study of Agentic Pull Requests on GitHub","created":"2026-01-01","cited_by_count":7,"area":"agents"},{"id":"2404.08517","title":"Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forward","created":"2024-04-12","cited_by_count":6,"area":null},{"id":"2412.14841","title":"Helping LLMs Improve Code Generation Using Feedback from Testing and Static Analysis","created":"2024-12-19","cited_by_count":6,"area":null},{"id":"2504.01850","title":"Code Red! On the Harmfulness of Applying Off-the-shelf Large Language Models to Programming Tasks","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2505.10494","title":"Can You Really Trust Code Copilots? Evaluating Large Language Models from a Code Security Perspective","created":"2025-05-15","cited_by_count":6,"area":null},{"id":"2508.03936","title":"ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants","created":"2025-08-05","cited_by_count":6,"area":"safety"},{"id":"2602.07422","title":"Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model","created":"2026-02-07","cited_by_count":6,"area":"alignment"},{"id":"2407.20529","title":"Can LLMs be Fooled? Investigating Vulnerabilities in LLMs","created":"2024-07-30","cited_by_count":5,"area":null},{"id":"2512.21132","title":"AutoBaxBuilder: Bootstrapping Code Security Benchmarking","created":"2025-12-24","cited_by_count":5,"area":"synth"},{"id":"2602.19547","title":"CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents","created":"2026-02-23","cited_by_count":5,"area":"agents"},{"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":"2412.10807","title":"Towards Action Hijacking of Large Language Model-based Agent","created":"2024-12-14","cited_by_count":4,"area":"agents"},{"id":"2504.15284","title":"EditLord: Learning Code Transformation Rules for Code Editing","created":"2025-03-10","cited_by_count":4,"area":null},{"id":"2506.07313","title":"SCGAgent: Recreating the Benefits of Reasoning Models for Secure Code Generation with Agentic Workflows","created":"2025-06-08","cited_by_count":4,"area":"agents"},{"id":"2506.17125","title":"Large Language Model Unlearning for Source Code","created":"2025-06-20","cited_by_count":4,"area":"safety"},{"id":"2510.13859","title":"Benchmarking Correctness and Security in Multi-Turn Code Generation","created":"2025-10-13","cited_by_count":4,"area":null},{"id":"2510.14113","title":"Toward Cybersecurity-Expert Small Language Models","created":"2025-10-15","cited_by_count":4,"area":null},{"id":"2511.01348","title":"The Future of Generative AI in Software Engineering: A Vision from Industry and Academia in the European GENIUS Project","created":"2025-11-03","cited_by_count":4,"area":null},{"id":"2604.18718","title":"Towards Optimal Agentic Architectures for Offensive Security Tasks","created":"2026-04-20","cited_by_count":4,"area":"agents"},{"id":"2402.04373","title":"The World of Generative AI: Deepfakes and Large Language Models","created":"2024-02-06","cited_by_count":3,"area":null},{"id":"2411.08813","title":"Rethinking CyberSecEval: An LLM-Aided Approach to Evaluation Critique","created":"2024-11-13","cited_by_count":3,"area":null},{"id":"2505.23634","title":"MCP Safety Training: Learning to Refuse Falsely Benign MCP Exploits using Improved Preference Alignment","created":"2025-05-29","cited_by_count":3,"area":"agents"},{"id":"2509.19360","title":"Semantic Representation Attack against Aligned Large Language Models","created":"2025-09-18","cited_by_count":3,"area":"alignment"},{"id":"2510.17862","title":"When \"Correct\" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?","created":"2025-10-15","cited_by_count":3,"area":"agents"},{"id":"2601.03699","title":"RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models","created":"2026-01-07","cited_by_count":3,"area":"safety"},{"id":"2604.09544","title":"Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types","created":"2026-04-10","cited_by_count":3,"area":"safety"},{"id":"2605.22643","title":"Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety","created":"2026-05-21","cited_by_count":3,"area":"agents"},{"id":"2404.18567","title":"Double Backdoored: Converting Code Large Language Model Backdoors to Traditional Malware via Adversarial Instruction Tuning Attacks","created":"2024-04-29","cited_by_count":2,"area":"safety"},{"id":"2410.23472","title":"Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2411.14571","title":"Learned, Lagged, LLM-splained: LLM Responses to End User Security Questions","created":"2024-11-21","cited_by_count":2,"area":null},{"id":"2412.18551","title":"Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability","created":"2024-12-24","cited_by_count":2,"area":null},{"id":"2510.12200","title":"HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities","created":"2025-10-14","cited_by_count":2,"area":"agents"},{"id":"2512.05439","title":"BEAVER: An Efficient Deterministic LLM Verifier","created":"2025-12-05","cited_by_count":2,"area":null},{"id":"2512.20677","title":"Learning-Based Automated Adversarial Red-Teaming for Robustness Evaluation of Large Language Models","created":"2025-12-21","cited_by_count":2,"area":"safety"},{"id":"2410.18114","title":"Bridging Today and the Future of Humanity: AI Safety in 2024 and Beyond","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2505.12185","title":"EVALOOOP: A Self-Consistency-Centered Framework for Assessing Large Language Model Robustness in Programming","created":"2025-05-18","cited_by_count":1,"area":"lr"},{"id":"2510.08329","title":"AutoRed: A Free-form Adversarial Prompt Generation Framework for Automated Red Teaming","created":"2025-10-09","cited_by_count":1,"area":"safety"},{"id":"2511.03898","title":"Secure Code Generation at Scale with Reflexion","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2511.20709","title":"DualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding Agents","created":"2025-11-24","cited_by_count":1,"area":"agents"},{"id":"2602.04894","title":"Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2603.10969","title":"TOSSS: a CVE-based Software Security Benchmark for Large Language Models","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2603.13384","title":"VulnAgent-R2: Evidence-Calibrated Multi-Agent Auditing for Repository-Level Vulnerability Detection","created":"2026-03-11","cited_by_count":1,"area":"agents"}],"next_cursor":"100"}