{"total":96,"rows":[{"id":"2501.04227","title":"Agent Laboratory: Using LLM Agents as Research Assistants","created":"2025-01-08","cited_by_count":425,"area":"agents"},{"id":"2412.04984","title":"Frontier Models are Capable of In-context Scheming","created":"2024-12-06","cited_by_count":287,"area":null},{"id":"2406.05590","title":"NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security","created":"2024-06-08","cited_by_count":93,"area":null},{"id":"2405.03644","title":"When LLMs Meet Cybersecurity: A Systematic Literature Review","created":"2024-05-06","cited_by_count":71,"area":null},{"id":"2505.02077","title":"Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents","created":"2025-05-04","cited_by_count":71,"area":"safety"},{"id":"2411.05185","title":"PentestAgent: Incorporating LLM Agents to Automated Penetration Testing","created":"2024-11-07","cited_by_count":47,"area":"agents"},{"id":"2412.01778","title":"HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing","created":"2024-12-02","cited_by_count":37,"area":"agents"},{"id":"2501.13411","title":"VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework","created":"2025-01-23","cited_by_count":31,"area":"agents"},{"id":"2409.14457","title":"Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends","created":"2024-09-22","cited_by_count":26,"area":null},{"id":"2407.02956","title":"IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization","created":"2024-07-03","cited_by_count":23,"area":null},{"id":"2408.04870","title":"ConfusedPilot: Confused Deputy Risks in RAG-based LLMs","created":"2024-08-09","cited_by_count":22,"area":"rag"},{"id":"2410.03225","title":"AutoPenBench: Benchmarking Generative Agents for Penetration Testing","created":"2024-10-04","cited_by_count":21,"area":"agents"},{"id":"2504.05408","title":"Frontier AI's Impact on the Cybersecurity Landscape","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2408.08902","title":"Audit-LLM: Multi-Agent Collaboration for Log-based Insider Threat Detection","created":"2024-08-12","cited_by_count":18,"area":"agents"},{"id":"2501.16466","title":"Incalmo: An Autonomous LLM-assisted System for Red Teaming Multi-Host Networks","created":"2025-01-27","cited_by_count":17,"area":"safety"},{"id":"2503.11917","title":"A Framework for Evaluating Emerging Cyberattack Capabilities of AI","created":"2025-03-14","cited_by_count":16,"area":null},{"id":"2406.12263","title":"Defending Against Social Engineering Attacks in the Age of LLMs","created":"2024-06-18","cited_by_count":15,"area":null},{"id":"2410.20911","title":"Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks","created":"2024-10-28","cited_by_count":15,"area":"safety"},{"id":"2504.07137","title":"Large Language Model (LLM) for Software Security: Code Analysis, Malware Analysis, Reverse Engineering","created":"2025-04-07","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":"2503.15552","title":"Personalized Attacks of Social Engineering in Multi-turn Conversations: LLM Agents for Simulation and Detection","created":"2025-03-18","cited_by_count":13,"area":"agents"},{"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":"2502.16730","title":"RapidPen: Fully Automated IP-to-Shell Penetration Testing with LLM-based Agents","created":"2025-02-23","cited_by_count":11,"area":"agents"},{"id":"2507.02424","title":"CyberRAG: An Agentic RAG cyber attack classification and reporting tool","created":"2025-07-03","cited_by_count":11,"area":"rag"},{"id":"2502.09755","title":"Jailbreak Attack Initializations as Extractors of Compliance Directions","created":"2025-02-13","cited_by_count":10,"area":"safety"},{"id":"2505.10321","title":"AutoPentest: Enhancing Vulnerability Management With Autonomous LLM Agents","created":"2025-05-15","cited_by_count":9,"area":"agents"},{"id":"2411.06493","title":"LProtector: An LLM-driven Vulnerability Detection System","created":"2024-11-10","cited_by_count":8,"area":null},{"id":"2505.18384","title":"Dynamic Risk Assessments for Offensive Cybersecurity Agents","created":"2025-05-23","cited_by_count":8,"area":"agents"},{"id":"2511.02780","title":"PoCo: Agentic Proof-of-Concept Exploit Generation for Smart Contracts","created":"2025-11-04","cited_by_count":8,"area":"agents"},{"id":"2505.06913","title":"RedTeamLLM: an Agentic AI framework for offensive security","created":"2025-05-11","cited_by_count":7,"area":"agents"},{"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":"2512.14233","title":"PentestEval: Benchmarking LLM-based Penetration Testing with Modular and Stage-Level Design","created":"2025-12-16","cited_by_count":7,"area":null},{"id":"2408.11650","title":"CIPHER: Cybersecurity Intelligent Penetration-testing Helper for Ethical Researcher","created":"2024-08-21","cited_by_count":6,"area":null},{"id":"2412.18770","title":"Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-box Neural Ranking Models","created":"2024-12-25","cited_by_count":6,"area":"lr"},{"id":"2509.14278","title":"Beyond Data Privacy: New Privacy Risks for Large Language Models","created":"2025-09-16","cited_by_count":6,"area":null},{"id":"2510.05605","title":"AutoPentester: An LLM Agent-based Framework for Automated Pentesting","created":"2025-10-07","cited_by_count":6,"area":"agents"},{"id":"2502.18528","title":"ARACNE: An LLM-Based Autonomous Shell Pentesting Agent","created":"2025-02-24","cited_by_count":5,"area":"agents"},{"id":"2508.07382","title":"Pentest-R1: Towards Autonomous Penetration Testing Reasoning Optimized via Two-Stage Reinforcement Learning","created":"2025-08-10","cited_by_count":5,"area":"lr"},{"id":"2512.11143","title":"Automated Penetration Testing with LLM Agents and Classical Planning","created":"2025-12-11","cited_by_count":5,"area":"agents"},{"id":"2409.16125","title":"Analyzing Probabilistic Methods for Evaluating Agent Capabilities","created":"2024-09-24","cited_by_count":4,"area":null},{"id":"2503.03170","title":"AttackSeqBench: Benchmarking the Capabilities of LLMs for Attack Sequences Understanding","created":"2025-03-05","cited_by_count":4,"area":null},{"id":"2503.04299","title":"Mapping AI Benchmark Data to Quantitative Risk Estimates Through Expert Elicitation","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2511.15998","title":"Hiding in the AI Traffic: Abusing MCP for LLM-Powered Agentic Red Teaming","created":"2025-11-20","cited_by_count":4,"area":"agents"},{"id":"2604.05719","title":"Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing","created":"2026-04-07","cited_by_count":4,"area":null},{"id":"2410.15396","title":"The Best Defense is a Good Offense: Countering LLM-Powered Cyberattacks","created":"2024-10-20","cited_by_count":3,"area":null},{"id":"2411.16642","title":"Preventing Jailbreak Prompts as Malicious Tools for Cybercriminals: A Cyber Defense Perspective","created":"2024-11-25","cited_by_count":3,"area":"safety"},{"id":"2503.03108","title":"OMNISEC: LLM-Driven Provenance-based Intrusion Detection via Retrieval-Augmented Behavior Prompting","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2505.07089","title":"RefPentester: A Knowledge-Informed Self-Reflective Penetration Testing Framework Based on Large Language Models","created":"2025-05-11","cited_by_count":3,"area":null},{"id":"2509.13021","title":"xOffense: An Autonomous Multi-Agent Framework for Penetration Testing with Domain-Adapted Large Language Models","created":"2025-09-16","cited_by_count":3,"area":"agents"},{"id":"2503.15546","title":"Enforcing Cybersecurity Constraints for LLM-driven Robot Agents for Online Transactions","created":"2025-03-17","cited_by_count":2,"area":"agents"},{"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":"2605.24949","title":"APT-Agent: Automated Penetration Testing using Large Language Models","created":"2026-05-24","cited_by_count":2,"area":"agents"},{"id":"2606.03811","title":"AI Agents Enable Adaptive Computer Worms","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2406.18783","title":"Psychological Profiling in Cybersecurity: A Look at LLMs and Psycholinguistic Features","created":"2024-06-26","cited_by_count":1,"area":null},{"id":"2410.18312","title":"Countering Autonomous Cyber Threats","created":"2024-10-23","cited_by_count":1,"area":null},{"id":"2502.08886","title":"Generative AI for Internet of Things Security: Challenges and Opportunities","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2502.11588","title":"A Unified Modeling Framework for Automated Penetration Testing","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2502.15506","title":"Construction and Evaluation of LLM-based agents for Semi-Autonomous penetration testing","created":"2025-02-21","cited_by_count":1,"area":"agents"},{"id":"2507.21113","title":"Vulnerability Mitigation System (VMS): LLM Agent and Evaluation Framework for Autonomous Penetration Testing","created":"2025-07-14","cited_by_count":1,"area":"agents"},{"id":"2510.11398","title":"Living Off the LLM: How LLMs Will Change Adversary Tactics","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2510.17521","title":"Cybersecurity AI: Evaluating Agentic Cybersecurity in Attack/Defense CTFs","created":"2025-10-20","cited_by_count":1,"area":"agents"},{"id":"2511.14195","title":"N-GLARE: An Non-Generative Latent Representation-Efficient LLM Safety Evaluator","created":"2025-11-18","cited_by_count":1,"area":"safety"},{"id":"2601.22720","title":"AEGIS: White-Box Attack Path Generation using LLMs and Training Effectiveness Evaluation for Large-Scale Cyber Defence Exercises","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2603.00960","title":"AWE: Adaptive Agents for Dynamic Web Penetration Testing","created":"2026-03-01","cited_by_count":1,"area":"agents"},{"id":"2604.05440","title":"LanG -- A Governance-Aware Agentic AI Platform for Unified Security Operations","created":"2026-04-07","cited_by_count":1,"area":"agents"},{"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":"2604.27143","title":"Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents","created":"2026-04-29","cited_by_count":1,"area":"agents"},{"id":"2605.06486","title":"Autonomous Adversary: Red-Teaming in the age of LLM","created":"2026-05-07","cited_by_count":1,"area":"agents"},{"id":"2605.07830","title":"CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios","created":"2026-05-08","cited_by_count":1,"area":"agents"},{"id":"2605.21773","title":"HIDBench: Benchmarking Large Language Models for Host-Based Intrusion Detection","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2606.25332","title":"Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2608.03009","title":"Tiny Enough to Break In: Agentic Remote Access Trojans Powered by Small Language Models","created":"2026-08-04","cited_by_count":1,"area":"agents"},{"id":"2608.05199","title":"Post-Hoc Trajectory-Risk Certification for Modular LLM-Based Security Agents","created":"2026-08-04","cited_by_count":1,"area":"agents"},{"id":"2608.20563","title":"Beyond End-to-End Success: Diagnosing Failures in Long-Horizon Security LLM Agents","created":"2026-08-20","cited_by_count":1,"area":"agents"},{"id":"2411.08003","title":"Can adversarial attacks by large language models be attributed?","created":"2024-11-12","cited_by_count":0,"area":null},{"id":"2412.04029","title":"Considerations Influencing Offense-Defense Dynamics From Artificial Intelligence","created":"2024-12-05","cited_by_count":0,"area":null},{"id":"2506.08693","title":"Recognition Without Mitigation: Ethical Frameworks in Autonomous Offensive-LLM Agent Research","created":"2025-06-10","cited_by_count":0,"area":"agents"},{"id":"2507.02057","title":"MGC: A Compiler Framework Exploiting Compositional Blindness in Aligned LLMs for Malware Generation","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2508.00478","title":"CyGATE: Game-Theoretic Cyber Attack-Defense Engine for Patch Strategy Optimization","created":"2025-08-01","cited_by_count":0,"area":null},{"id":"2509.14289","title":"From Capabilities to Performance: Evaluating Key Functional Properties of LLM Architectures in Penetration Testing","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2603.24221","title":"Environment-Grounded Multi-Agent Workflow for Autonomous Penetration Testing","created":"2026-03-25","cited_by_count":0,"area":"agents"},{"id":"2604.00704","title":"AutoEG: Exploiting Known Third-Party Vulnerabilities in Black-Box Web Applications","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2605.00741","title":"Self-Adaptive Multi-Agent LLM-Based Security Pattern Selection for IoT Systems","created":"2026-05-01","cited_by_count":0,"area":"agents"},{"id":"2605.02346","title":"APIOT: Autonomous Vulnerability Management Across Bare-Metal Industrial OT Networks","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.04499","title":"Pen-Strategist: A Reasoning Framework for Penetration Testing Strategy Formation and Analysis","created":"2026-05-06","cited_by_count":0,"area":"lr"},{"id":"2605.21694","title":"PocketAgents: A Manifest-Driven Library of Autonomous Defense Agents","created":"2026-05-20","cited_by_count":0,"area":"agents"},{"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":"2606.24496","title":"Red-Teaming the Agentic Red-Team","created":"2026-06-23","cited_by_count":0,"area":"agents"},{"id":"2607.09653","title":"VEXAIoT: Autonomous IoT Vulnerability EXploitation using AI Agents","created":"2026-07-10","cited_by_count":0,"area":"agents"},{"id":"2608.21423","title":"Agentic Security: A Systematization of Tools, Failure Modes, and Design Laws for LLM-Driven Penetration Testing","created":"2026-08-16","cited_by_count":0,"area":"agents"},{"id":"2609.01185","title":"Reveree: Diagnosing LLM Reverse-Engineering Agents","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.02647","title":"PrimSynth: An Agentic Approach to Discover, Validate, and Synthesize Exploit Primitives for Linux Kernel Vulnerabilities","created":"2026-09-02","cited_by_count":0,"area":"agents"},{"id":"2609.11852","title":"BlueSTAR: Tiered Agentic Architecture for Autonomous Cyber Defense","created":"2026-09-10","cited_by_count":0,"area":"agents"},{"id":"2609.16694","title":"Toward Secure AI-Powered Penetration Testing Agents: Security Threats, Guardrails, and Architectural Perspectives","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"id":"2609.28572","title":"Where Cyber Agents Struggle: Bottleneck Analysis of Multi-Stage LLM Agents","created":"2026-09-23","cited_by_count":0,"area":"agents"}],"next_cursor":null}