{"list":"closest","total":53,"rows":[{"id":"2510.01359","title":"Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks","created":"2025-10-01","cited_by_count":7},{"id":"2510.00311","title":"CORTEX: Collaborative LLM Agents for High-Stakes Alert Triage","created":"2025-09-30","cited_by_count":14},{"id":"2509.24698","title":"LISA Technical Report: An Agentic Framework for Smart Contract Auditing","created":"2025-09-29","cited_by_count":2},{"id":"2509.23614","title":"PSG-Agent: Personality-Aware Safety Guardrail for LLM-based Agents","created":"2025-09-28","cited_by_count":12},{"id":"2509.17488","title":"Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agents","created":"2025-09-22","cited_by_count":36},{"id":"2509.08646","title":"Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations","created":"2025-09-10","cited_by_count":7},{"id":"2509.01835","title":"From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEs","created":"2025-09-01","cited_by_count":18},{"id":"2508.21579","title":"Agentic Discovery and Validation of Android App Vulnerabilities","created":"2025-08-29","cited_by_count":4},{"id":"2508.21323","title":"LLM-driven Provenance Forensics for Threat Investigation and Detection","created":"2025-08-29","cited_by_count":5},{"id":"2508.20816","title":"Multi-Agent Penetration Testing AI for the Web","created":"2025-08-28","cited_by_count":20},{"id":"2508.20643","title":"CyberSleuth: Autonomous Blue-Team LLM Agent for Web Attack Forensics","created":"2025-08-28","cited_by_count":3},{"id":"2508.10880","title":"Searching for Privacy Risks in LLM Agents via Simulation","created":"2025-08-14","cited_by_count":22},{"id":"2508.06457","title":"ScamAgents: How AI Agents Can Simulate Human-Level Scam Calls","created":"2025-08-08","cited_by_count":4},{"id":"2507.14201","title":"ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation","created":"2025-07-14","cited_by_count":15},{"id":"2506.19676","title":"A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures","created":"2025-06-24","cited_by_count":57},{"id":"2506.11791","title":"SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks","created":"2025-06-13","cited_by_count":75},{"id":"2506.05739","title":"To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt","created":"2025-06-06","cited_by_count":15},{"id":"2506.01055","title":"Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution","created":"2025-06-01","cited_by_count":26},{"id":"2505.23847","title":"Seven Security Challenges in Cross-domain Multi-agent LLM Systems","created":"2025-05-28","cited_by_count":12},{"id":"2505.13076","title":"The Hidden Dangers of Browsing AI Agents","created":"2025-05-19","cited_by_count":11},{"id":"2505.10321","title":"AutoPentest: Enhancing Vulnerability Management With Autonomous LLM Agents","created":"2025-05-15","cited_by_count":9},{"id":"2505.05849","title":"AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents","created":"2025-05-09","cited_by_count":42},{"id":"2504.19956","title":"Securing Agentic AI: A Comprehensive Threat Model and Mitigation Framework for Generative AI Agents","created":"2025-04-28","cited_by_count":32},{"id":"2504.14064","title":"DoomArena: A framework for Testing AI Agents Against Evolving Security Threats","created":"2025-04-18","cited_by_count":32},{"id":"2504.11703","title":"Progent: Securing AI Agents with Privilege Control","created":"2025-04-16","cited_by_count":141},{"id":"2503.18666","title":"AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents","created":"2025-03-24","cited_by_count":223},{"id":"2503.17332","title":"CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities","created":"2025-03-21","cited_by_count":96},{"id":"2503.15547","title":"Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents","created":"2025-03-17","cited_by_count":87},{"id":"2503.04957","title":"SafeArena: Evaluating the Safety of Autonomous Web Agents","created":"2025-03-06","cited_by_count":102},{"id":"2503.03704","title":"Memory Injection Attacks on LLM Agents via Query-Only Interaction","created":"2025-03-05","cited_by_count":144},{"id":"2503.00061","title":"Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents","created":"2025-02-27","cited_by_count":125},{"id":"2502.20383","title":"Why Are Web AI Agents More Vulnerable Than Standalone LLMs? A Security Analysis","created":"2025-02-27","cited_by_count":27},{"id":"2502.18528","title":"ARACNE: An LLM-Based Autonomous Shell Pentesting Agent","created":"2025-02-24","cited_by_count":5},{"id":"2502.14847","title":"Red-Teaming LLM Multi-Agent Systems via Communication Attacks","created":"2025-02-20","cited_by_count":122},{"id":"2502.11448","title":"AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection","created":"2025-02-17","cited_by_count":89},{"id":"2502.10931","title":"D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security","created":"2025-02-15","cited_by_count":20},{"id":"2502.08586","title":"Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks","created":"2025-02-12","cited_by_count":49},{"id":"2502.05206","title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety","created":"2025-02-02","cited_by_count":67},{"id":"2501.13411","title":"VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework","created":"2025-01-23","cited_by_count":31},{"id":"2412.16682","title":"The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents","created":"2024-12-21","cited_by_count":99},{"id":"2412.10807","title":"Towards Action Hijacking of Large Language Model-based Agent","created":"2024-12-14","cited_by_count":4},{"id":"2412.01778","title":"HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing","created":"2024-12-02","cited_by_count":37},{"id":"2411.09523","title":"Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents","created":"2024-11-14","cited_by_count":65},{"id":"2411.05185","title":"PentestAgent: Incorporating LLM Agents to Automated Penetration Testing","created":"2024-11-07","cited_by_count":47},{"id":"2410.09024","title":"AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents","created":"2024-10-11","cited_by_count":437},{"id":"2410.03225","title":"AutoPenBench: Benchmarking Generative Agents for Penetration Testing","created":"2024-10-04","cited_by_count":21},{"id":"2410.02644","title":"Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents","created":"2024-10-03","cited_by_count":369},{"id":"2407.12784","title":"AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases","created":"2024-07-17","cited_by_count":429},{"id":"2406.01637","title":"Teams of LLM Agents can Exploit Zero-Day Vulnerabilities","created":"2024-06-02","cited_by_count":95},{"id":"2404.08144","title":"LLM Agents can Autonomously Exploit One-day Vulnerabilities","created":"2024-04-11","cited_by_count":128},{"id":"2403.16073","title":"Combining Fine-Tuning and LLM-based Agents for Intuitive Smart Contract Auditing with Justifications","created":"2024-03-24","cited_by_count":41},{"id":"2403.02691","title":"InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents","created":"2024-03-05","cited_by_count":538},{"id":"2402.11208","title":"Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents","created":"2024-02-17","cited_by_count":137}],"next_cursor":null}