{"total":230,"rows":[{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477,"area":null},{"id":"2409.00138","title":"PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action","created":"2024-08-29","cited_by_count":171,"area":null},{"id":"2409.11295","title":"EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage","created":"2024-09-17","cited_by_count":150,"area":"agents"},{"id":"2406.07933","title":"Large Language Model Unlearning via Embedding-Corrupted Prompts","created":"2024-06-12","cited_by_count":116,"area":"safety"},{"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":"2405.05175","title":"AirGapAgent: Protecting Privacy-Conscious Conversational Agents","created":"2024-05-08","cited_by_count":94,"area":"agents"},{"id":"2403.08715","title":"SOTOPIA-$\\pi$: Interactive Learning of Socially Intelligent Language Agents","created":"2024-03-13","cited_by_count":93,"area":"agents"},{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2503.09780","title":"AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents","created":"2025-03-12","cited_by_count":82,"area":"agents"},{"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":"2502.02384","title":"STAIR: Improving Safety Alignment with Introspective Reasoning","created":"2025-02-04","cited_by_count":77,"area":"lr"},{"id":"2402.01822","title":"Building Guardrails for Large Language Models","created":"2024-02-02","cited_by_count":65,"area":"safety"},{"id":"2406.17975","title":"SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)","created":"2024-06-25","cited_by_count":59,"area":"safety"},{"id":"2501.17070","title":"Contextual Agent Security: A Policy for Every Purpose","created":"2025-01-28","cited_by_count":59,"area":null},{"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":"2406.07057","title":"MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models","created":"2024-06-11","cited_by_count":53,"area":"mllm"},{"id":"2406.17626","title":"CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference","created":"2024-06-25","cited_by_count":51,"area":"safety"},{"id":"2410.17520","title":"MobileSafetyBench: Evaluating Safety of Autonomous Agents in Mobile Device Control","created":"2024-10-23","cited_by_count":51,"area":"agents"},{"id":"2311.09538","title":"Reducing Privacy Risks in Online Self-Disclosures with Language Models","created":"2023-11-16","cited_by_count":47,"area":null},{"id":"2407.11438","title":"Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild","created":"2024-07-16","cited_by_count":47,"area":null},{"id":"2311.04235","title":"Can LLMs Follow Simple Rules?","created":"2023-11-06","cited_by_count":46,"area":null},{"id":"2408.12787","title":"LLM-PBE: Assessing Data Privacy in Large Language Models","created":"2024-08-23","cited_by_count":41,"area":null},{"id":"2412.06878","title":"SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations","created":"2024-12-09","cited_by_count":38,"area":"safety"},{"id":"2406.11149","title":"GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory","created":"2024-06-17","cited_by_count":37,"area":null},{"id":"2408.02373","title":"Operationalizing Contextual Integrity in Privacy-Conscious Assistants","created":"2024-08-05","cited_by_count":37,"area":null},{"id":"2409.13903","title":"CI-Bench: Benchmarking Contextual Integrity of AI Assistants on Synthetic Data","created":"2024-09-20","cited_by_count":37,"area":"synth"},{"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":"2410.14273","title":"REEF: Representation Encoding Fingerprints for Large Language Models","created":"2024-10-18","cited_by_count":36,"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":"2402.11755","title":"SPML: A DSL for Defending Language Models Against Prompt Attacks","created":"2024-02-19","cited_by_count":34,"area":null},{"id":"2311.09447","title":"How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities","created":"2023-11-15","cited_by_count":33,"area":null},{"id":"2402.11597","title":"Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once?","created":"2024-02-18","cited_by_count":30,"area":null},{"id":"2510.15186","title":"MAGPIE: A benchmark for Multi-AGent contextual PrIvacy Evaluation","created":"2025-10-16","cited_by_count":29,"area":"agents"},{"id":"2502.04506","title":"When One LLM Drools, Multi-LLM Collaboration Rules","created":"2025-02-06","cited_by_count":28,"area":null},{"id":"2506.17209","title":"Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency","created":"2025-06-20","cited_by_count":27,"area":"safety"},{"id":"2502.18509","title":"Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents","created":"2025-02-22","cited_by_count":26,"area":"agents"},{"id":"2502.11090","title":"SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks","created":"2025-02-16","cited_by_count":23,"area":"safety"},{"id":"2410.03055","title":"Permissive Information-Flow Analysis for Large Language Models","created":"2024-10-04","cited_by_count":22,"area":null},{"id":"2508.10880","title":"Searching for Privacy Risks in LLM Agents via Simulation","created":"2025-08-14","cited_by_count":22,"area":"agents"},{"id":"2407.04952","title":"Granular Privacy Control for Geolocation with Vision Language Models","created":"2024-07-06","cited_by_count":21,"area":"mllm"},{"id":"2407.12344","title":"The Better Angels of Machine Personality: How Personality Relates to LLM Safety","created":"2024-07-17","cited_by_count":21,"area":null},{"id":"2505.01976","title":"A Survey on Privacy Risks and Protection in Large Language Models","created":"2025-05-04","cited_by_count":21,"area":"safety"},{"id":"2501.14940","title":"CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models","created":"2025-01-24","cited_by_count":20,"area":"alignment"},{"id":"2509.14284","title":"The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration","created":"2025-09-16","cited_by_count":20,"area":"agents"},{"id":"2402.19465","title":"Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models","created":"2024-02-29","cited_by_count":18,"area":null},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2505.13312","title":"GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection","created":"2025-05-19","cited_by_count":17,"area":"safety"},{"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":"2402.02987","title":"Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models","created":"2024-02-05","cited_by_count":16,"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":"2509.00559","title":"Social World Models","created":"2025-08-30","cited_by_count":16,"area":"wm"},{"id":"2511.05359","title":"ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations","created":"2025-11-07","cited_by_count":16,"area":"agents"},{"id":"2412.06966","title":"Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research","created":"2024-12-09","cited_by_count":15,"area":"safety"},{"id":"2501.08617","title":"RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation","created":"2025-01-15","cited_by_count":15,"area":"alignment"},{"id":"2410.02912","title":"Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation","created":"2024-10-03","cited_by_count":14,"area":null},{"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":"2604.21308","title":"CI-Work: Benchmarking Contextual Integrity in Enterprise LLM Agents","created":"2026-04-23","cited_by_count":14,"area":"agents"},{"id":"2606.24535","title":"Governed Shared Memory for Multi-Agent LLM Systems","created":"2026-06-23","cited_by_count":13,"area":"agents"},{"id":"2512.24848","title":"PrivacyBench: A Conversational Benchmark for Evaluating Privacy in Personalized AI","created":"2025-12-31","cited_by_count":12,"area":null},{"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":"2405.15523","title":"The Mosaic Memory of Large Language Models","created":"2024-05-24","cited_by_count":10,"area":null},{"id":"2512.08417","title":"Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs","created":"2025-12-09","cited_by_count":10,"area":"agents"},{"id":"2402.01994","title":"Human-Centered Privacy Research in the Age of Large Language Models","created":"2024-02-03","cited_by_count":9,"area":null},{"id":"2505.12402","title":"Automated Profile Inference with Language Model Agents","created":"2025-05-18","cited_by_count":9,"area":"agents"},{"id":"2505.20118","title":"TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent","created":"2025-05-26","cited_by_count":9,"area":null},{"id":"2506.13009","title":"Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective","created":"2025-06-16","cited_by_count":9,"area":"safety"},{"id":"2506.17788","title":"Bayesian Social Deduction with Graph-Informed Language Models","created":"2025-06-21","cited_by_count":9,"area":null},{"id":"2605.17634","title":"AI Agents May Always Fall for Prompt Injections","created":"2026-05-17","cited_by_count":9,"area":"safety"},{"id":"2406.03749","title":"NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human","created":"2024-06-06","cited_by_count":8,"area":null},{"id":"2406.11007","title":"Threat Modelling and Risk Analysis for Large Language Model (LLM)-Powered Applications","created":"2024-06-16","cited_by_count":8,"area":"safety"},{"id":"2505.14585","title":"Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning","created":"2025-05-20","cited_by_count":8,"area":"lr"},{"id":"2510.03662","title":"Operationalizing Data Minimization for Privacy-Preserving LLM Prompting","created":"2025-10-04","cited_by_count":8,"area":null},{"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":"2511.05784","title":"DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning","created":"2025-11-08","cited_by_count":7,"area":"lr"},{"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":"2605.09823","title":"CalBench: Evaluating Coordination-Privacy Trade-offs in Multi-Agent LLMs","created":"2026-05-10","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":"2506.17336","title":"PPMI: Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases","created":"2025-06-19","cited_by_count":6,"area":"lr"},{"id":"2506.20737","title":"MAGPIE: A dataset for Multi-AGent contextual PrIvacy Evaluation","created":"2025-06-25","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":"2603.07557","title":"AgentRaft: Automated Detection of Data Over-Exposure in LLM Agents","created":"2026-03-08","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":"2402.07812","title":"Retrieval Augmented Thought Process for Private Data Handling in Healthcare","created":"2024-02-12","cited_by_count":5,"area":"lr"},{"id":"2409.07489","title":"RAGent: Retrieval-based Access Control Policy Generation","created":"2024-09-08","cited_by_count":5,"area":null},{"id":"2502.12328","title":"LM Agents for Coordinating Multi-User Information Gathering","created":"2025-02-17","cited_by_count":5,"area":null},{"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":"2510.12950","title":"An Investigation of Memorization Risk in Healthcare Foundation Models","created":"2025-10-14","cited_by_count":5,"area":null},{"id":"2512.01109","title":"How do we measure privacy in text? A survey of text anonymization metrics","created":"2025-11-30","cited_by_count":5,"area":null},{"id":"2601.05076","title":"Chain-of-Sanitized-Thoughts: Plugging PII Leakage in CoT of Large Reasoning Models","created":"2026-01-08","cited_by_count":5,"area":"lr"}],"next_cursor":"100"}