{"total":171,"rows":[{"id":"2412.14470","title":"Agent-SafetyBench: Evaluating the Safety of LLM Agents","created":"2024-12-19","cited_by_count":306,"area":"agents"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2506.14866","title":"OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents","created":"2025-06-17","cited_by_count":111,"area":"agents"},{"id":"2503.09648","title":"A Survey on Trustworthy LLM Agents: Threats and Countermeasures","created":"2025-03-12","cited_by_count":96,"area":"agents"},{"id":"2602.20156","title":"Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks","created":"2026-02-23","cited_by_count":90,"area":"agents"},{"id":"2503.09780","title":"AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents","created":"2025-03-12","cited_by_count":82,"area":"agents"},{"id":"2507.06134","title":"OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety","created":"2025-07-08","cited_by_count":75,"area":"agents"},{"id":"2412.15701","title":"Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration","created":"2024-12-20","cited_by_count":65,"area":"agents"},{"id":"2504.11281","title":"The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections","created":"2025-04-15","cited_by_count":59,"area":"agents"},{"id":"2410.17127","title":"PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles","created":"2024-10-22","cited_by_count":57,"area":null},{"id":"2502.12561","title":"UXAgent: An LLM Agent-Based Usability Testing Framework for Web Design","created":"2025-02-18","cited_by_count":40,"area":"agents"},{"id":"2502.17041","title":"PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance","created":"2025-02-24","cited_by_count":37,"area":null},{"id":"2502.01822","title":"Firewalls to Secure Dynamic LLM Agentic Networks","created":"2025-02-03","cited_by_count":36,"area":"agents"},{"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,"area":"agents"},{"id":"2505.24019","title":"LLM Agents Should Employ Security Principles","created":"2025-05-29","cited_by_count":29,"area":"agents"},{"id":"2510.23883","title":"Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges","created":"2025-10-27","cited_by_count":28,"area":"agents"},{"id":"2602.11510","title":"AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems","created":"2026-02-12","cited_by_count":25,"area":"agents"},{"id":"2503.08669","title":"SOPBench: Evaluating Language Agents at Following Standard Operating Procedures and Constraints","created":"2025-03-11","cited_by_count":23,"area":"agents"},{"id":"2505.10924","title":"A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?","created":"2025-05-16","cited_by_count":23,"area":"agents"},{"id":"2508.10880","title":"Searching for Privacy Risks in LLM Agents via Simulation","created":"2025-08-14","cited_by_count":22,"area":"agents"},{"id":"2508.07667","title":"1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning","created":"2025-08-11","cited_by_count":17,"area":"lr"},{"id":"2510.01645","title":"Position: Privacy Is Not Just Memorization!","created":"2025-10-02","cited_by_count":17,"area":null},{"id":"2410.11876","title":"Rescriber: Smaller-LLM-Powered User-Led Data Minimization for LLM-Based Chatbots","created":"2024-10-10","cited_by_count":16,"area":null},{"id":"2509.10723","title":"Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human Oversight","created":"2025-09-12","cited_by_count":16,"area":"agents"},{"id":"2511.05359","title":"ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations","created":"2025-11-07","cited_by_count":16,"area":"agents"},{"id":"2411.01344","title":"Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agent","created":"2024-11-02","cited_by_count":14,"area":"agents"},{"id":"2505.11063","title":"Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction","created":"2025-05-16","cited_by_count":14,"area":"lr"},{"id":"2604.21308","title":"CI-Work: Benchmarking Contextual Integrity in Enterprise LLM Agents","created":"2026-04-23","cited_by_count":14,"area":"agents"},{"id":"2502.20490","title":"EgoNormia: Benchmarking Physical Social Norm Understanding","created":"2025-02-27","cited_by_count":13,"area":null},{"id":"2506.11680","title":"Malicious LLM-Based Conversational AI Makes Users Reveal Personal Information","created":"2025-06-13","cited_by_count":13,"area":null},{"id":"2504.17934","title":"Toward a Human-Centered Evaluation Framework for Trustworthy LLM-Powered GUI Agents","created":"2025-04-24","cited_by_count":11,"area":"agents"},{"id":"2506.12241","title":"Privacy Reasoning in Ambiguous Contexts","created":"2025-06-13","cited_by_count":11,"area":"lr"},{"id":"2512.16310","title":"Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation","created":"2025-12-18","cited_by_count":11,"area":"agents"},{"id":"2605.14271","title":"Auditing Agent Harness Safety","created":"2026-05-14","cited_by_count":11,"area":"agents"},{"id":"2504.09407","title":"UXAgent: A System for Simulating Usability Testing of Web Design with LLM Agents","created":"2025-04-13","cited_by_count":10,"area":"agents"},{"id":"2509.01211","title":"Web Fraud Attacks Against LLM-Driven Multi-Agent Systems","created":"2025-09-01","cited_by_count":10,"area":"agents"},{"id":"2603.04902","title":"AgentSCOPE: Evaluating Contextual Privacy Across Agentic Workflows","created":"2026-03-05","cited_by_count":10,"area":"agents"},{"id":"2506.07524","title":"TAI3: Testing Agent Integrity in Interpreting User Intent","created":"2025-06-09","cited_by_count":9,"area":"agents"},{"id":"2510.01670","title":"Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness","created":"2025-10-02","cited_by_count":9,"area":"agents"},{"id":"2604.13954","title":"HINTBench: Horizon-agent Intrinsic Non-attack Trajectory Benchmark","created":"2026-04-15","cited_by_count":9,"area":"agents"},{"id":"2605.17634","title":"AI Agents May Always Fall for Prompt Injections","created":"2026-05-17","cited_by_count":9,"area":"safety"},{"id":"2509.25624","title":"STAC: When Innocent Tools Form Dangerous Chains for LLM Agents","created":"2025-09-30","cited_by_count":8,"area":"agents"},{"id":"2510.03662","title":"Operationalizing Data Minimization for Privacy-Preserving LLM Prompting","created":"2025-10-04","cited_by_count":8,"area":null},{"id":"2603.03205","title":"Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use","created":"2026-03-03","cited_by_count":8,"area":"lr"},{"id":"2603.05520","title":"Information-Theoretic Privacy Control for Sequential Multi-Agent LLM Systems","created":"2026-02-13","cited_by_count":8,"area":"agents"},{"id":"2609.29429","title":"Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures","created":"2026-09-24","cited_by_count":8,"area":"safety"},{"id":"2601.17887","title":"When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents","created":"2026-01-25","cited_by_count":7,"area":"agents"},{"id":"2601.19956","title":"VoxPrivacy: A Benchmark for Evaluating Interactional Privacy of Speech Language Models","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2602.13840","title":"PrivAct: Internalizing Contextual Privacy Preservation via Multi-Agent Preference Training","created":"2026-02-14","cited_by_count":7,"area":"agents"},{"id":"2603.02983","title":"Contextualized Privacy Defense for LLM Agents","created":"2026-03-03","cited_by_count":7,"area":"agents"},{"id":"2603.05923","title":"Learning Next Action Predictors from Human-Computer Interaction","created":"2026-03-06","cited_by_count":7,"area":null},{"id":"2604.01487","title":"AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social Networks","created":"2026-04-01","cited_by_count":7,"area":"agents"},{"id":"2605.09530","title":"MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents","created":"2026-05-10","cited_by_count":7,"area":"agents"},{"id":"2605.09823","title":"CalBench: Evaluating Coordination-Privacy Trade-offs in Multi-Agent LLMs","created":"2026-05-10","cited_by_count":7,"area":"agents"},{"id":"2605.17830","title":"Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents","created":"2026-05-18","cited_by_count":7,"area":"agents"},{"id":"2606.28061","title":"ToolPrivacyBench: Benchmarking Purpose-Bound Privacy in Tool-Using LLM Agents","created":"2026-06-26","cited_by_count":7,"area":"agents"},{"id":"2409.03735","title":"Privacy Bias in Language Models: A Contextual Integrity-based Auditing Metric","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2410.03026","title":"Estimating Privacy Leakage of Augmented Contextual Knowledge in Language Models","created":"2024-10-03","cited_by_count":6,"area":null},{"id":"2506.20737","title":"MAGPIE: A dataset for Multi-AGent contextual PrIvacy Evaluation","created":"2025-06-25","cited_by_count":6,"area":"agents"},{"id":"2508.13465","title":"LM Agents May Fail to Act on Their Own Risk Knowledge","created":"2025-08-19","cited_by_count":6,"area":"agents"},{"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":"2601.15220","title":"Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models","created":"2026-01-21","cited_by_count":6,"area":null},{"id":"2605.22786","title":"LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems","created":"2026-05-21","cited_by_count":6,"area":"agents"},{"id":"2606.00152","title":"PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say","created":"2026-05-29","cited_by_count":6,"area":"agents"},{"id":"2606.01317","title":"SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces","created":"2026-05-31","cited_by_count":6,"area":"agents"},{"id":"2607.01236","title":"Safeguarding LLM Agents from Misalignment through Provenance Analysis","created":"2026-05-01","cited_by_count":6,"area":"agents"},{"id":"2505.15805","title":"Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question Answering","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2510.07505","title":"PEAR: Planner-Executor Agent Robustness Benchmark","created":"2025-10-08","cited_by_count":5,"area":"agents"},{"id":"2605.23989","title":"Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security","created":"2026-05-17","cited_by_count":5,"area":"agents"},{"id":"2608.28945","title":"Automated Researchers Can Mitigate Well-characterized Alignment Failures","created":"2026-08-28","cited_by_count":5,"area":null},{"id":"2505.14549","title":"Can Large Language Models Really Recognize Your Name?","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2506.13324","title":"Towards Pervasive Distributed Agentic Generative AI -- A State of The Art","created":"2025-06-16","cited_by_count":4,"area":"agents"},{"id":"2512.05065","title":"Personalizing Agent Privacy Decisions via Logical Entailment","created":"2025-12-04","cited_by_count":4,"area":"agents"},{"id":"2603.10268","title":"SpecOps: A Fully Automated AI Agent Testing Framework in Real-World GUI Environments","created":"2026-03-10","cited_by_count":4,"area":"agents"},{"id":"2603.18382","title":"From Weak Cues to Real Identities: Evaluating Inference-Driven De-Anonymization in LLM Agents","created":"2026-03-19","cited_by_count":4,"area":"agents"},{"id":"2605.19127","title":"POLAR-Bench: A Diagnostic Benchmark for Privacy-Utility Trade-offs in LLM Agents","created":"2026-05-18","cited_by_count":4,"area":"agents"},{"id":"2509.10018","title":"GAMA: A General Anonymizing Multi-Agent System for Privacy Preservation Enhanced by Domain Rules and Disproof Mechanism","created":"2025-09-12","cited_by_count":3,"area":"agents"},{"id":"2509.21712","title":"It's My Agent, Not Me: Personal Privacy Boundaries in AI-Delegated Information Sharing","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2602.03183","title":"Privasis: Synthesizing the Largest \"Public\" Private Dataset from Scratch","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2602.13516","title":"SPILLage: Agentic Oversharing on the Web","created":"2026-02-13","cited_by_count":3,"area":"agents"},{"id":"2603.11862","title":"You Told Me to Do It: Measuring Instructional Text-induced Private Data Leakage in LLM Agents","created":"2026-03-12","cited_by_count":3,"area":"agents"},{"id":"2604.00986","title":"Do Phone-Use Agents Respect Your Privacy?","created":"2026-04-01","cited_by_count":3,"area":null},{"id":"2605.02307","title":"SOTOPIA-TOM: Evaluating Privacy and Information Management in Multi-Agent Interaction with Theory of Mind","created":"2026-05-04","cited_by_count":3,"area":"agents"},{"id":"2605.14454","title":"LiSA: Lifelong Safety Adaptation via Conservative Policy Induction","created":"2026-05-14","cited_by_count":3,"area":"safety"},{"id":"2606.04067","title":"Need to Know: Contextual-Integrity-Grounded Query Rewriting for Privacy-Conscious LLM Delegation","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2606.23189","title":"Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?","created":"2026-06-22","cited_by_count":3,"area":"agents"},{"id":"2606.23217","title":"MuPPET: A Benchmark for Contextual Privacy of LLM Assistants in Multi-Party Conversations","created":"2026-06-22","cited_by_count":3,"area":"agents"},{"id":"2606.30383","title":"Whose Side Is Your Agent On? Multi-Party Principal Loyalty in LLM Agents","created":"2026-06-29","cited_by_count":3,"area":null},{"id":"2608.08300","title":"Mitigating Over-Personalization in LLMs via Structured Memory","created":"2026-08-08","cited_by_count":3,"area":null},{"id":"2508.03991","title":"Galaxy: A Cognition-Centered Framework for Proactive, Privacy-Preserving, and Self-Evolving LLM Agents","created":"2025-08-06","cited_by_count":2,"area":"agents"},{"id":"2509.12152","title":"Beyond PII: How Users Attempt to Estimate and Mitigate Implicit LLM Inference","created":"2025-09-15","cited_by_count":2,"area":null},{"id":"2510.02356","title":"Measuring Physical-World Privacy Awareness of Large Language Models: An Evaluation Benchmark","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2510.10943","title":"The Social Cost of Intelligence: Emergence, Propagation, and Amplification of Stereotypical Bias in Multi-Agent Systems","created":"2025-10-13","cited_by_count":2,"area":"agents"},{"id":"2512.08104","title":"AgentCrypt: Advancing Privacy and (Secure) Computation in AI Agent Collaboration","created":"2025-12-08","cited_by_count":2,"area":"agents"},{"id":"2601.09152","title":"PrivacyReasoner: Can LLM Emulate a Human-like Privacy Mind?","created":"2026-01-14","cited_by_count":2,"area":"lr"},{"id":"2603.18245","title":"Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety","created":"2026-03-18","cited_by_count":2,"area":"agents"},{"id":"2606.13949","title":"Minim: Privacy-Aware Minimal View for Agents via Trusted Local Sanitization","created":"2026-06-11","cited_by_count":2,"area":"agents"},{"id":"2606.21710","title":"PrivacyAlign: Contextual Privacy Alignment for LLM Agents","created":"2026-06-19","cited_by_count":2,"area":"agents"},{"id":"2607.05318","title":"PiSAs: Benchmarking Contextual Integrity in Multi-User Agentic Systems","created":"2026-07-06","cited_by_count":2,"area":"agents"},{"id":"2510.04465","title":"Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents","created":"2025-10-06","cited_by_count":1,"area":null}],"next_cursor":"100"}