{"total":285,"rows":[{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651,"area":"safety"},{"id":"2308.03825","title":"\"Do Anything Now\": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models","created":"2023-08-07","cited_by_count":489,"area":"safety"},{"id":"2404.01833","title":"Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack","created":"2024-04-02","cited_by_count":390,"area":"safety"},{"id":"2402.06363","title":"StruQ: Defending Against Prompt Injection with Structured Queries","created":"2024-02-09","cited_by_count":375,"area":"safety"},{"id":"2304.05197","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","created":"2023-04-11","cited_by_count":333,"area":"safety"},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2410.05451","title":"SecAlign: Defending Against Prompt Injection with Preference Optimization","created":"2024-10-07","cited_by_count":210,"area":"alignment"},{"id":"2406.01171","title":"Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization","created":"2024-06-03","cited_by_count":208,"area":null},{"id":"2402.07841","title":"Do Membership Inference Attacks Work on Large Language Models?","created":"2024-02-12","cited_by_count":195,"area":"safety"},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194,"area":"safety"},{"id":"2402.00888","title":"Security and Privacy Challenges of Large Language Models: A Survey","created":"2024-01-30","cited_by_count":186,"area":"safety"},{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177,"area":null},{"id":"2310.07298","title":"Beyond Memorization: Violating Privacy Via Inference with Large Language Models","created":"2023-10-11","cited_by_count":175,"area":null},{"id":"2309.17410","title":"Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks","created":"2023-09-29","cited_by_count":158,"area":null},{"id":"2307.01881","title":"ProPILE: Probing Privacy Leakage in Large Language Models","created":"2023-07-04","cited_by_count":129,"area":null},{"id":"2405.15032","title":"Aya 23: Open Weight Releases to Further Multilingual Progress","created":"2024-05-23","cited_by_count":123,"area":null},{"id":"2410.23123","title":"On Memorization of Large Language Models in Logical Reasoning","created":"2024-10-30","cited_by_count":117,"area":"lr"},{"id":"2312.17673","title":"Jatmo: Prompt Injection Defense by Task-Specific Finetuning","created":"2023-12-29","cited_by_count":106,"area":"safety"},{"id":"2407.12043","title":"The Art of Saying No: Contextual Noncompliance in Language Models","created":"2024-07-02","cited_by_count":105,"area":null},{"id":"2404.08676","title":"ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming","created":"2024-04-06","cited_by_count":98,"area":"safety"},{"id":"2402.05668","title":"JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs","created":"2024-02-08","cited_by_count":95,"area":"safety"},{"id":"2403.18421","title":"BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text","created":"2024-03-27","cited_by_count":86,"area":null},{"id":"2308.12833","title":"Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities","created":"2023-08-24","cited_by_count":82,"area":null},{"id":"2402.17840","title":"Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems","created":"2024-02-27","cited_by_count":76,"area":"rag"},{"id":"2403.01749","title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text","created":"2024-03-04","cited_by_count":76,"area":"synth"},{"id":"2406.18682","title":"The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm","created":"2024-06-26","cited_by_count":70,"area":"safety"},{"id":"2307.09218","title":"A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning","created":"2023-07-16","cited_by_count":69,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"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":"2312.03724","title":"DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer","created":"2023-11-27","cited_by_count":57,"area":null},{"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":"2310.15007","title":"Did the Neurons Read your Book? Document-level Membership Inference for Large Language Models","created":"2023-10-23","cited_by_count":56,"area":"safety"},{"id":"2406.10328","title":"From Pixels to Prose: A Large Dataset of Dense Image Captions","created":"2024-06-14","cited_by_count":54,"area":"mllm"},{"id":"2310.10383","title":"Privacy in Large Language Models: Attacks, Defenses and Future Directions","created":"2023-10-16","cited_by_count":51,"area":null},{"id":"2404.13627","title":"NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surrounding","created":"2024-04-21","cited_by_count":51,"area":null},{"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":"2402.00351","title":"Machine Unlearning for Image-to-Image Generative Models","created":"2024-02-01","cited_by_count":47,"area":"safety"},{"id":"2305.16157","title":"Training Data Extraction From Pre-trained Language Models: A Survey","created":"2023-05-25","cited_by_count":45,"area":null},{"id":"2403.04786","title":"Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models","created":"2024-03-03","cited_by_count":44,"area":null},{"id":"2305.06212","title":"Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services","created":"2023-05-10","cited_by_count":43,"area":null},{"id":"2407.02552","title":"RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs","created":"2024-07-02","cited_by_count":43,"area":"alignment"},{"id":"2407.03211","title":"How Does Quantization Affect Multilingual LLMs?","created":"2024-07-03","cited_by_count":43,"area":null},{"id":"2405.19103","title":"Voice Jailbreak Attacks Against GPT-4o","created":"2024-05-29","cited_by_count":42,"area":"safety"},{"id":"2408.12787","title":"LLM-PBE: Assessing Data Privacy in Large Language Models","created":"2024-08-23","cited_by_count":41,"area":null},{"id":"2304.14827","title":"ChatGPT Evaluation on Sentence Level Relations: A Focus on Temporal, Causal, and Discourse Relations","created":"2023-04-28","cited_by_count":40,"area":null},{"id":"2310.18362","title":"SoK: Memorization in General-Purpose Large Language Models","created":"2023-10-24","cited_by_count":37,"area":null},{"id":"2311.04044","title":"PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models","created":"2023-11-07","cited_by_count":37,"area":null},{"id":"2404.10618","title":"Private Attribute Inference from Images with Vision-Language Models","created":"2024-04-16","cited_by_count":37,"area":"mllm"},{"id":"2411.14110","title":"Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications","created":"2024-11-21","cited_by_count":37,"area":"rag"},{"id":"2310.09266","title":"User Inference Attacks on Large Language Models","created":"2023-10-13","cited_by_count":36,"area":null},{"id":"2310.15469","title":"The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks","created":"2023-10-24","cited_by_count":36,"area":null},{"id":"2310.10077","title":"Prompt Packer: Deceiving LLMs through Compositional Instruction with Hidden Attacks","created":"2023-10-16","cited_by_count":35,"area":"safety"},{"id":"2309.12444","title":"Foundation Metrics for Evaluating Effectiveness of Healthcare Conversations Powered by Generative AI","created":"2023-09-21","cited_by_count":32,"area":null},{"id":"2310.09130","title":"Split-and-Denoise: Protect large language model inference with local differential privacy","created":"2023-10-13","cited_by_count":32,"area":null},{"id":"2403.00871","title":"Teach LLMs to Phish: Stealing Private Information from Language Models","created":"2024-03-01","cited_by_count":32,"area":null},{"id":"2312.11658","title":"Traces of Memorisation in Large Language Models for Code","created":"2023-12-18","cited_by_count":29,"area":"safety"},{"id":"2410.02650","title":"Undesirable Memorization in Large Language Models: A Survey","created":"2024-10-03","cited_by_count":29,"area":null},{"id":"2305.12707","title":"Quantifying Association Capabilities of Large Language Models and Its Implications on Privacy Leakage","created":"2023-05-22","cited_by_count":28,"area":null},{"id":"2406.05948","title":"Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models","created":"2024-06-10","cited_by_count":28,"area":"safety"},{"id":"2405.10989","title":"Learnable Privacy Neurons Localization in Language Models","created":"2024-05-16","cited_by_count":27,"area":null},{"id":"2310.09639","title":"DPZero: Private Fine-Tuning of Language Models without Backpropagation","created":"2023-10-14","cited_by_count":26,"area":null},{"id":"2401.00676","title":"Digger: Detecting Copyright Content Mis-usage in Large Language Model Training","created":"2024-01-01","cited_by_count":25,"area":null},{"id":"2404.06001","title":"Privacy Preserving Prompt Engineering: A Survey","created":"2024-04-09","cited_by_count":25,"area":null},{"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":"2407.02943","title":"PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding","created":"2024-07-03","cited_by_count":24,"area":null},{"id":"2410.07959","title":"COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act","created":"2024-10-10","cited_by_count":24,"area":null},{"id":"2503.06808","title":"Privacy Auditing of Large Language Models","created":"2025-03-09","cited_by_count":23,"area":"safety"},{"id":"2409.11423","title":"Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data","created":"2024-09-12","cited_by_count":22,"area":"synth"},{"id":"2502.03052","title":"Understanding and Enhancing the Transferability of Jailbreaking Attacks","created":"2025-02-05","cited_by_count":22,"area":"safety"},{"id":"2309.00087","title":"Large language models in medicine: the potentials and pitfalls","created":"2023-08-31","cited_by_count":21,"area":null},{"id":"2408.02559","title":"Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information","created":"2024-08-05","cited_by_count":20,"area":"agents"},{"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":"2307.02599","title":"Evade ChatGPT Detectors via A Single Space","created":"2023-07-05","cited_by_count":18,"area":null},{"id":"2308.15727","title":"Quantifying and Analyzing Entity-level Memorization in Large Language Models","created":"2023-08-30","cited_by_count":18,"area":null},{"id":"2405.09113","title":"Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization","created":"2024-05-15","cited_by_count":18,"area":"safety"},{"id":"2410.04068","title":"ECon: On the Detection and Resolution of Evidence Conflicts","created":"2024-10-05","cited_by_count":18,"area":null},{"id":"2305.15008","title":"Are Chatbots Ready for Privacy-Sensitive Applications? An Investigation into Input Regurgitation and Prompt-Induced Sanitization","created":"2023-05-24","cited_by_count":17,"area":null},{"id":"2311.15792","title":"Rethinking Privacy in Machine Learning Pipelines from an Information Flow Control Perspective","created":"2023-11-27","cited_by_count":16,"area":null},{"id":"2408.11006","title":"Security Attacks on LLM-based Code Completion Tools","created":"2024-08-20","cited_by_count":16,"area":"safety"},{"id":"2510.15001","title":"VaultGemma: A Differentially Private Gemma Model","created":"2025-10-15","cited_by_count":16,"area":null},{"id":"2307.10476","title":"What can we learn from Data Leakage and Unlearning for Law?","created":"2023-07-19","cited_by_count":15,"area":"safety"},{"id":"2307.16680","title":"On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook","created":"2023-07-31","cited_by_count":15,"area":"diffusion"},{"id":"2406.03880","title":"Memorization in deep learning: A survey","created":"2024-06-06","cited_by_count":15,"area":null},{"id":"2407.08583","title":"The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective","created":"2024-07-11","cited_by_count":15,"area":"mllm"},{"id":"2501.18532","title":"Differentially Private Steering for Large Language Model Alignment","created":"2025-01-30","cited_by_count":15,"area":"alignment"},{"id":"2502.19726","title":"Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training","created":"2025-02-27","cited_by_count":15,"area":"safety"},{"id":"2310.02469","title":"PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners","created":"2023-10-03","cited_by_count":14,"area":null},{"id":"2312.11513","title":"Maatphor: Automated Variant Analysis for Prompt Injection Attacks","created":"2023-12-12","cited_by_count":14,"area":"safety"},{"id":"2408.13247","title":"An In-Depth Investigation of Data Collection in LLM App Ecosystems","created":"2024-08-23","cited_by_count":14,"area":null},{"id":"2412.16504","title":"Privacy in Fine-tuning Large Language Models: Attacks, Defenses, and Future Directions","created":"2024-12-21","cited_by_count":14,"area":"safety"},{"id":"2504.19373","title":"Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models","created":"2025-04-27","cited_by_count":14,"area":null},{"id":"2406.09325","title":"REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space","created":"2024-06-13","cited_by_count":13,"area":"safety"},{"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":"2408.07291","title":"Evaluating LLM-based Personal Information Extraction and Countermeasures","created":"2024-08-14","cited_by_count":12,"area":"safety"},{"id":"2410.08327","title":"Evaluating Differentially Private Synthetic Data Generation in High-Stakes Domains","created":"2024-10-10","cited_by_count":12,"area":"synth"},{"id":"2504.09593","title":"ControlNET: A Firewall for RAG-based LLM System","created":"2025-04-13","cited_by_count":12,"area":"rag"},{"id":"2309.08303","title":"Self-Consistent Narrative Prompts on Abductive Natural Language Inference","created":"2023-09-15","cited_by_count":11,"area":null},{"id":"2312.07876","title":"Causality Analysis for Evaluating the Security of Large Language Models","created":"2023-12-13","cited_by_count":11,"area":"alignment"},{"id":"2407.21248","title":"Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens","created":"2024-07-30","cited_by_count":11,"area":null}],"next_cursor":"100"}