{"total":69,"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":"2505.24832","title":"How much do language models memorize?","created":"2025-05-30","cited_by_count":61,"area":null},{"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":"2409.19798","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":"2411.02902","title":"Membership Inference Attacks against Large Vision-Language Models","created":"2024-11-05","cited_by_count":33,"area":"mllm"},{"id":"2502.00306","title":"Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation","created":"2025-02-01","cited_by_count":26,"area":"rag"},{"id":"2503.06808","title":"Privacy Auditing of Large Language Models","created":"2025-03-09","cited_by_count":23,"area":"safety"},{"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":"2410.04207","title":"Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models","created":"2024-10-05","cited_by_count":22,"area":null},{"id":"2503.17514","title":"Language Models May Verbatim Complete Text They Were Not Explicitly Trained On","created":"2025-03-21","cited_by_count":21,"area":null},{"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":"2410.03537","title":"Ward: Provable RAG Dataset Inference via LLM Watermarks","created":"2024-10-04","cited_by_count":16,"area":"safety"},{"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":"2502.02260","title":"Position: Adversarial ML for LLMs Is Not Making Any Progress","created":"2025-02-04","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":"2410.07582","title":"Detecting Training Data of Large Language Models via Expectation Maximization","created":"2024-10-10","cited_by_count":13,"area":"safety"},{"id":"2506.13972","title":"Membership Inference Attacks as Privacy Tools: Reliability, Disparity and Ensemble","created":"2025-06-16","cited_by_count":11,"area":"safety"},{"id":"2411.19876","title":"LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states","created":"2024-11-29","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":"2506.13009","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":"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":"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":"2504.13416","title":"STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings","created":"2025-04-18","cited_by_count":8,"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":"2507.18725","title":"The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models","created":"2025-07-24","cited_by_count":7,"area":"safety"},{"id":"2412.13475","title":"A Statistical and Multi-Perspective Revisiting of the Membership Inference Attack in Large Language Models","created":"2024-12-18","cited_by_count":6,"area":"safety"},{"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":"2408.05968","title":"Nob-MIAs: Non-biased Membership Inference Attacks Assessment on Large Language Models with Ex-Post Dataset Construction","created":"2024-08-12","cited_by_count":5,"area":"safety"},{"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":"2605.28591","title":"Models That Know How Evaluations Are Designed Score Safer","created":"2026-05-27","cited_by_count":4,"area":null},{"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":"2504.18349","title":"Revisiting Data Auditing in Large Vision-Language Models","created":"2025-04-25","cited_by_count":3,"area":"mllm"},{"id":"2505.00020","title":"Beyond Public Access in LLM Pre-Training Data","created":"2025-04-24","cited_by_count":3,"area":"safety"},{"id":"2506.06057","title":"Hey, That's My Data! Token-Only Dataset Inference in Large Language Models","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2509.05449","title":"Neural Breadcrumbs: Membership Inference Attacks on LLMs Through Hidden State and Attention Pattern Analysis","created":"2025-09-05","cited_by_count":3,"area":"safety"},{"id":"2510.05699","title":"Membership Inference Attacks on Tokenizers of Large Language Models","created":"2025-10-07","cited_by_count":3,"area":"safety"},{"id":"2606.17464","title":"CheckMIABench: Firm Foundations For Membership Inference Attacks on Language Models","created":"2026-06-16","cited_by_count":3,"area":"safety"},{"id":"2412.08549","title":"Watermarking Training Data of Music Generation Models","created":"2024-12-11","cited_by_count":2,"area":"safety"},{"id":"2506.06003","title":"What Really is a Member? Discrediting Membership Inference via Poisoning","created":"2025-06-06","cited_by_count":2,"area":"safety"},{"id":"2510.05582","title":"(Token-Level) InfoRMIA: Stronger Membership Inference and Memorization Assessment for LLMs","created":"2025-10-07","cited_by_count":2,"area":"safety"},{"id":"2511.20799","title":"Memories Retrieved from Many Paths: A Multi-Prefix Framework for Robust Detection of Training Data Leakage in Large Language Models","created":"2025-11-25","cited_by_count":2,"area":null},{"id":"2601.04301","title":"Quantifying the Effect of Test Set Contamination on Generative Evaluations","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2603.28378","title":"Membership Inference Attacks against Large Audio Language Models","created":"2026-03-30","cited_by_count":2,"area":"safety"},{"id":"2604.03598","title":"AttackEval: A Systematic Empirical Study of Prompt Injection Attack Effectiveness Against Large Language Models","created":"2026-04-04","cited_by_count":2,"area":"safety"},{"id":"2410.03640","title":"Real-World Benchmarks Make Membership Inference Attacks Fail on Diffusion Models","created":"2024-10-04","cited_by_count":1,"area":"diffusion"},{"id":"2410.04454","title":"Inner-Probe: Discovering Copyright-related Data Generation in LLM Architecture","created":"2024-10-06","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":"2508.10404","title":"Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation","created":"2025-08-14","cited_by_count":1,"area":"safety"},{"id":"2603.01053","title":"Turning Black Box into White Box: Dataset Distillation Leaks","created":"2026-03-01","cited_by_count":1,"area":null},{"id":"2411.07449","title":"Tracing the Roots: Leveraging Temporal Dynamics in Diffusion Trajectories for Origin Attribution","created":"2024-11-12","cited_by_count":0,"area":"diffusion"},{"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":"2511.14084","title":"Observational Auditing of Label Privacy","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2512.02786","title":"FiMMIA: scaling semantic perturbation-based membership inference across modalities","created":"2025-12-02","cited_by_count":0,"area":"safety"},{"id":"2512.17075","title":"Perturb Your Data: Paraphrase-Guided Training Data Watermarking","created":"2025-12-18","cited_by_count":0,"area":null},{"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":"2603.19375","title":"Automated Membership Inference Attacks (AutoMIA): Discovering MIA Signal Computations using LLM Agents","created":"2026-03-19","cited_by_count":0,"area":"agents"},{"id":"2603.22707","title":"Detecting Non-Membership in LLM Training Data via Rank Correlations","created":"2026-03-24","cited_by_count":0,"area":null},{"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":"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":"2608.00144","title":"Leak It: Per-Document Extraction Beyond Aggregate Membership Inference","created":"2026-07-31","cited_by_count":0,"area":"safety"},{"id":"2608.07914","title":"When Is Benchmark Contamination Detectable? Information Limits and Power-Calibrated Audits","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.12652","title":"Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection","created":"2026-08-12","cited_by_count":0,"area":"safety"},{"id":"2609.06190","title":"One Perturbation Is Not Enough: Identifiability and Blind Baselines for Behavioral AI Evaluation","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.10830","title":"Detectable Only Where It Is Confounded: What Verified Duplication Counts Say About Membership Evidence in Language Models","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.38830","title":"SparLeak: Privacy Leakage from Sparse Attention in LLM Inference on Shared GPUs","created":"2026-09-30","cited_by_count":0,"area":"inference"},{"id":"2610.16152","title":"WildTrace: Evaluating Training Data Detection in Realistic Large-Scale LLM Post-Training","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.17332","title":"COMPASS: Membership Inference Attack Against Vision Large Language Models via Adaptive Noise Calibration","created":"2026-10-12","cited_by_count":0,"area":"safety"}],"next_cursor":null}