{"total":103,"rows":[{"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":"2502.12893","title":"H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking","created":"2025-02-18","cited_by_count":99,"area":"lr"},{"id":"2411.19799","title":"INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge","created":"2024-11-29","cited_by_count":86,"area":null},{"id":"2406.10890","title":"RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models","created":"2024-06-16","cited_by_count":78,"area":"safety"},{"id":"2406.16201","title":"Blind Baselines Beat Membership Inference Attacks for Foundation Models","created":"2024-06-23","cited_by_count":69,"area":"safety"},{"id":"2406.15968","title":"ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods","created":"2024-06-23","cited_by_count":64,"area":"safety"},{"id":"2410.02879","title":"Position: LLM Unlearning Benchmarks are Weak Measures of Progress","created":"2024-10-03","cited_by_count":63,"area":"safety"},{"id":"2506.13759","title":"Discrete Diffusion in Large Language and Multimodal Models: A Survey","created":"2025-06-16","cited_by_count":61,"area":"mllm"},{"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":"2409.14781","title":"Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method","created":"2024-09-23","cited_by_count":55,"area":null},{"id":"2409.19798","title":"Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data","created":"2024-09-29","cited_by_count":50,"area":"safety"},{"id":"2405.20446","title":"Is My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented Generation","created":"2024-05-30","cited_by_count":44,"area":"rag"},{"id":"2507.11412","title":"Seq vs Seq: An Open Suite of Paired Encoders and Decoders","created":"2025-07-15","cited_by_count":38,"area":null},{"id":"2502.18943","title":"Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models","created":"2025-02-26","cited_by_count":37,"area":"safety"},{"id":"2407.06443","title":"Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment","created":"2024-07-08","cited_by_count":25,"area":"alignment"},{"id":"2409.13745","title":"Context-Aware Membership Inference Attacks against Pre-trained Large Language Models","created":"2024-09-11","cited_by_count":22,"area":"safety"},{"id":"2409.03363","title":"Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding","created":"2024-09-05","cited_by_count":20,"area":null},{"id":"2506.03179","title":"Vid-SME: Membership Inference Attacks against Large Video Understanding Models","created":"2025-05-29","cited_by_count":19,"area":"mllm"},{"id":"2407.17417","title":"Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?","created":"2024-07-24","cited_by_count":18,"area":"safety"},{"id":"2406.10218","title":"Semantic Membership Inference Attack against Large Language Models","created":"2024-06-14","cited_by_count":17,"area":"safety"},{"id":"2410.17711","title":"Beware of Calibration Data for Pruning Large Language Models","created":"2024-10-23","cited_by_count":15,"area":null},{"id":"2502.00678","title":"How Contaminated Is Your Benchmark? Quantifying Dataset Leakage in Large Language Models with Kernel Divergence","created":"2025-02-02","cited_by_count":15,"area":null},{"id":"2502.02514","title":"Privacy Attacks on Image AutoRegressive Models","created":"2025-02-04","cited_by_count":15,"area":"diffusion"},{"id":"2503.16402","title":"The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination","created":"2025-03-20","cited_by_count":15,"area":null},{"id":"2410.07582","title":"Detecting Training Data of Large Language Models via Expectation Maximization","created":"2024-10-10","cited_by_count":13,"area":"safety"},{"id":"2503.14043","title":"Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions","created":"2025-03-18","cited_by_count":12,"area":null},{"id":"2506.02089","title":"SALAD: Systematic Assessment of Machine Unlearning on LLM-Aided Hardware Design","created":"2025-06-02","cited_by_count":12,"area":"safety"},{"id":"2511.04583","title":"Jr. AI Scientist and Its Risk Report: Autonomous Scientific Exploration from a Baseline Paper","created":"2025-11-06","cited_by_count":12,"area":null},{"id":"2508.04117","title":"Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks","created":"2025-08-06","cited_by_count":11,"area":"lr"},{"id":"2506.05314","title":"Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2506.10424","title":"SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks","created":"2025-06-12","cited_by_count":10,"area":"safety"},{"id":"2506.21551","title":"Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test","created":"2025-06-26","cited_by_count":10,"area":"moe"},{"id":"2507.18302","title":"LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models","created":"2025-07-24","cited_by_count":9,"area":"safety"},{"id":"2510.02386","title":"On The Fragility of Benchmark Contamination Detection in Reasoning Models","created":"2025-09-30","cited_by_count":9,"area":"lr"},{"id":"2410.10880","title":"Fine-tuning can Help Detect Pretraining Data from Large Language Models","created":"2024-10-09","cited_by_count":8,"area":null},{"id":"2501.03941","title":"Synthetic Data Privacy Metrics","created":"2025-01-07","cited_by_count":8,"area":null},{"id":"2504.13416","title":"STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings","created":"2025-04-18","cited_by_count":8,"area":null},{"id":"2510.27055","title":"Detecting Data Contamination in LLMs via In-Context Learning","created":"2025-10-30","cited_by_count":8,"area":null},{"id":"2511.14045","title":"Auditing Data Membership in Reinforcement Learning With Verifiable Rewards","created":"2025-11-18","cited_by_count":8,"area":null},{"id":"2505.22860","title":"Permissioned LLMs: Enforcing Access Control in Large Language Models","created":"2025-05-28","cited_by_count":7,"area":null},{"id":"2506.15271","title":"Unlocking Post-hoc Dataset Inference with Synthetic Data","created":"2025-06-18","cited_by_count":7,"area":"synth"},{"id":"2508.09603","title":"The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage","created":"2025-08-13","cited_by_count":7,"area":"safety"},{"id":"2601.02751","title":"Window-based Membership Inference Attacks Against Fine-tuned Large Language Models","created":"2026-01-06","cited_by_count":7,"area":"safety"},{"id":"2606.14748","title":"Is My Vision-Language Data in Your AI? Membership Inference Test (MINT) Demo 2","created":"2026-06-05","cited_by_count":7,"area":"safety"},{"id":"2506.05126","title":"Membership Inference Attacks on Sequence Models","created":"2025-06-05","cited_by_count":6,"area":"safety"},{"id":"2506.19399","title":"Automated Detection of Pre-training Text in Black-box LLMs","created":"2025-06-24","cited_by_count":6,"area":null},{"id":"2501.08454","title":"Tag&Tab: Pretraining Data Detection in Large Language Models Using Keyword-Based Membership Inference Attack","created":"2025-01-14","cited_by_count":5,"area":"safety"},{"id":"2601.20125","title":"Membership Inference Attacks Against Fine-tuned Diffusion Language Models","created":"2026-01-27","cited_by_count":5,"area":"diffusion"},{"id":"2407.02960","title":"ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets","created":"2024-07-03","cited_by_count":4,"area":null},{"id":"2505.15209","title":"DUSK: Do Not Unlearn Shared Knowledge","created":"2025-05-21","cited_by_count":4,"area":"safety"},{"id":"2511.01952","title":"Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing","created":"2025-11-03","cited_by_count":4,"area":"mllm"},{"id":"2601.18110","title":"AttenMIA: LLM Membership Inference Attack through Attention Signals","created":"2026-01-26","cited_by_count":4,"area":"safety"},{"id":"2406.12044","title":"ARTIST: Improving the Generation of Text-rich Images with Disentangled Diffusion Models and Large Language Models","created":"2024-06-17","cited_by_count":3,"area":"diffusion"},{"id":"2409.06067","title":"MLLM-LLaVA-FL: Multimodal Large Language Model Assisted Federated Learning","created":"2024-09-09","cited_by_count":3,"area":"mllm"},{"id":"2410.07030","title":"Clean Evaluations on Contaminated Visual Language Models","created":"2024-10-09","cited_by_count":3,"area":"mllm"},{"id":"2501.11786","title":"Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detection","created":"2025-01-20","cited_by_count":3,"area":"synth"},{"id":"2505.00020","title":"Beyond Public Access in LLM Pre-Training Data","created":"2025-04-24","cited_by_count":3,"area":"safety"},{"id":"2508.07054","title":"Membership and Memorization in LLM Knowledge Distillation","created":"2025-08-09","cited_by_count":3,"area":"distill"},{"id":"2510.05699","title":"Membership Inference Attacks on Tokenizers of Large Language Models","created":"2025-10-07","cited_by_count":3,"area":"safety"},{"id":"2601.15111","title":"Auditing Language Model Unlearning via Information Decomposition","created":"2026-01-21","cited_by_count":3,"area":"safety"},{"id":"2404.17143","title":"Quantifying Memorization and Detecting Training Data of Pre-trained Language Models using Japanese Newspaper","created":"2024-04-26","cited_by_count":2,"area":null},{"id":"2504.08300","title":"Large Language Models Could Be Rote Learners","created":"2025-04-11","cited_by_count":2,"area":null},{"id":"2505.03392","title":"Automatic Calibration for Membership Inference Attack on Large Language Models","created":"2025-05-06","cited_by_count":2,"area":"safety"},{"id":"2506.07399","title":"MrM: Black-Box Membership Inference Attacks against Multimodal RAG Systems","created":"2025-06-09","cited_by_count":2,"area":"mllm"},{"id":"2506.20941","title":"Revisiting the Past: Data Unlearning with Model State History","created":"2025-06-26","cited_by_count":2,"area":"safety"},{"id":"2512.09654","title":"Membership and Dataset Inference Attacks on Large Audio Generative Models","created":"2025-12-10","cited_by_count":2,"area":"safety"},{"id":"2602.11792","title":"Detecting RLVR Training Data via Structural Convergence of Reasoning","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2603.28378","title":"Membership Inference Attacks against Large Audio Language Models","created":"2026-03-30","cited_by_count":2,"area":"safety"},{"id":"2501.13983","title":"AdEval: Alignment-based Dynamic Evaluation to Mitigate Data Contamination in Large Language Models","created":"2025-01-23","cited_by_count":1,"area":null},{"id":"2502.17358","title":"DIS-CO: Discovering Copyrighted Content in VLMs Training Data","created":"2025-02-24","cited_by_count":1,"area":"mllm"},{"id":"2506.06060","title":"Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2508.01268","title":"Win-k: Improved Membership Inference Attacks on Small Language Models","created":"2025-08-02","cited_by_count":1,"area":"safety"},{"id":"2510.19773","title":"Estimating Model-Level Membership Inference Vulnerability Without Reference Models","created":"2025-10-22","cited_by_count":1,"area":"safety"},{"id":"2511.20068","title":"PRADA: Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Images","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2512.05341","title":"When Forgetting Builds Reliability: LLM Unlearning for Reliable Hardware Code Generation","created":"2025-12-05","cited_by_count":1,"area":"safety"},{"id":"2601.14994","title":"Obscuring Data Contamination Through Translation: Evidence from Arabic Corpora","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2603.24857","title":"AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective","created":"2026-03-25","cited_by_count":1,"area":"safety"},{"id":"2604.03199","title":"Learning the Signature of Memorization in Autoregressive Language Models","created":"2026-04-03","cited_by_count":1,"area":"safety"},{"id":"2605.24079","title":"TRACER: A Semantic-Aware Framework for Fine-Grained Contamination Detection in Code LLMs","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2609.05976","title":"Beyond Cross-Lingual Transfer: Benchmarking Propagation Boundaries in Multilingual LLM Unlearning","created":"2026-09-05","cited_by_count":1,"area":"safety"},{"id":"2411.03363","title":"TDDBench: A Benchmark for Training data detection","created":"2024-11-05","cited_by_count":0,"area":"safety"},{"id":"2503.20800","title":"Evidencing Unauthorized Training Data from AI Generated Content using Information Isotopes","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2506.16460","title":"Black-Box Privacy Attacks on Shared Representations in Multitask Learning","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2507.17389","title":"Are AI Coders Snitches? An Empirical Study of Pretraining Data Detection on Code Large Language Models","created":"2025-07-23","cited_by_count":0,"area":null},{"id":"2510.25941","title":"RECAP: Reproducing Copyrighted Data from LLMs Training with an Agentic Pipeline","created":"2025-10-29","cited_by_count":0,"area":"agents"},{"id":"2511.00192","title":"EL-MIA: Quantifying Membership Inference Risks of Sensitive Entities in LLMs","created":"2025-10-31","cited_by_count":0,"area":"safety"},{"id":"2512.03121","title":"Lost in Modality: Evaluating the Effectiveness of Text-Based Membership Inference Attacks on Large Multimodal Models","created":"2025-12-02","cited_by_count":0,"area":"mllm"},{"id":"2512.13352","title":"On the Effectiveness of Membership Inference in Targeted Data Extraction from Large Language Models","created":"2025-12-15","cited_by_count":0,"area":"safety"},{"id":"2601.12937","title":"On the Evidentiary Limits of Membership Inference for Copyright Auditing","created":"2026-01-19","cited_by_count":0,"area":"safety"},{"id":"2602.19020","title":"Learning to Detect Language Model Training Data via Active Reconstruction","created":"2026-02-22","cited_by_count":0,"area":"safety"},{"id":"2603.03054","title":"PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue Systems","created":"2026-03-03","cited_by_count":0,"area":"alignment"},{"id":"2604.01014","title":"AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-Exploration","created":"2026-04-01","cited_by_count":0,"area":"agents"},{"id":"2604.01904","title":"Combating Data Laundering in LLM Training","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2606.07996","title":"MC-PDD: Masked Corpus-Level Pretraining Data Detection for Black-Box Large Language Models","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2606.10066","title":"A Controlled Audit of Pretraining Contamination in Public Medical Vision-Language Benchmarks","created":"2026-06-08","cited_by_count":0,"area":"mllm"},{"id":"2606.24408","title":"Natural Identifiers for Privacy and Data Audits in Large Language Models","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2607.04339","title":"One Framework for All: Cross-Modal Membership Inference for Generative Models","created":"2026-07-05","cited_by_count":0,"area":"safety"},{"id":"2607.14242","title":"Implicit Reasoning Steering via Concept Chaining","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"id":"2608.11922","title":"LODESTAR: Robust Entropy-Based Answer Selection in Retrieval-Augmented Generation for Question Answering -- Directing Frozen-LLM Entropy with a Reinforcement-Learned Prompt Polarizer under Misleading Passages","created":"2026-08-12","cited_by_count":0,"area":"rag"},{"id":"2608.27782","title":"Memorization Is Not Extraction: Tight Differential-Privacy Bounds and Audit Blind Spots","created":"2026-08-27","cited_by_count":0,"area":null}],"next_cursor":"100"}