{"total":59,"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":"2505.16831","title":"Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs","created":"2025-05-22","cited_by_count":42,"area":"safety"},{"id":"2410.18966","title":"Does Data Contamination Detection Work (Well) for LLMs? A Survey and Evaluation on Detection Assumptions","created":"2024-10-24","cited_by_count":26,"area":null},{"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":"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":"2503.19338","title":"Membership Inference Attacks on Large-Scale Models: A Survey","created":"2025-03-25","cited_by_count":18,"area":"mllm"},{"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":"2506.06112","title":"Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness","created":"2025-06-06","cited_by_count":11,"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":"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":"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":"2407.02596","title":"Towards More Realistic Extraction Attacks: An Adversarial Perspective","created":"2024-07-02","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":"2603.05520","title":"Information-Theoretic Privacy Control for Sequential Multi-Agent LLM Systems","created":"2026-02-13","cited_by_count":8,"area":"agents"},{"id":"2604.00419","title":"G-Drift MIA: Membership Inference via Gradient-Induced Feature Drift in LLMs","created":"2026-04-01","cited_by_count":8,"area":"safety"},{"id":"2506.15271","title":"Unlocking Post-hoc Dataset Inference with Synthetic Data","created":"2025-06-18","cited_by_count":7,"area":"synth"},{"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":"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":"2506.16666","title":"The Hitchhiker's Guide to Efficient, End-to-End, and Tight DP Auditing","created":"2025-06-20","cited_by_count":5,"area":null},{"id":"2601.20125","title":"Membership Inference Attacks Against Fine-tuned Diffusion Language Models","created":"2026-01-27","cited_by_count":5,"area":"diffusion"},{"id":"2510.09655","title":"Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique","created":"2025-10-07","cited_by_count":4,"area":null},{"id":"2605.28591","title":"Models That Know How Evaluations Are Designed Score Safer","created":"2026-05-27","cited_by_count":4,"area":null},{"id":"2606.06946","title":"Auditing Training Data in Domain-adapted LLMs: LoRA-MINT","created":"2026-06-05","cited_by_count":4,"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":"2512.16292","title":"In-Context Probing for Membership Inference in Fine-Tuned Language Models","created":"2025-12-18","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":"2503.21088","title":"ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging","created":"2025-03-27","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":"2602.02819","title":"Causal Evaluation of Membership Inference Attacks","created":"2026-02-02","cited_by_count":2,"area":"safety"},{"id":"2604.12342","title":"CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2505.11837","title":"On Membership Inference Attacks in Knowledge Distillation","created":"2025-05-17","cited_by_count":1,"area":"safety"},{"id":"2509.21208","title":"CLaw: Benchmarking Chinese Legal Knowledge in Large Language Models - A Fine-grained Corpus and Reasoning Analysis","created":"2025-09-25","cited_by_count":1,"area":"lr"},{"id":"2510.18674","title":"Exploring Membership Inference Vulnerabilities in Clinical Large Language Models","created":"2025-10-21","cited_by_count":1,"area":"safety"},{"id":"2601.10496","title":"Model See, Model Do? Exposure-Aware Evaluation of Bug-vs-Fix Preference in Code LLMs","created":"2026-01-15","cited_by_count":1,"area":null},{"id":"2601.15874","title":"SoK: Challenges in Tabular Membership Inference Attacks","created":"2026-01-22","cited_by_count":1,"area":"safety"},{"id":"2605.30348","title":"LLMSurgeon: Diagnosing Data Mixture of Large Language Models","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2508.15141","title":"Towards Reliable and Generalizable Differentially Private Machine Learning (Extended Version)","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2509.04169","title":"Privacy Risks in Time Series Forecasting: User- and Record-Level Membership Inference","created":"2025-09-04","cited_by_count":0,"area":"safety"},{"id":"2510.05753","title":"Empirical Comparison of Membership Inference Attacks in Deep Transfer Learning","created":"2025-10-07","cited_by_count":0,"area":"safety"},{"id":"2510.23074","title":"Fast-MIA: Efficient and Scalable Membership Inference for LLMs","created":"2025-10-27","cited_by_count":0,"area":"safety"},{"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":"2511.14084","title":"Observational Auditing of Label Privacy","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2512.01514","title":"Label Forensics: Interpreting Hard Labels in Black-Box Text Classifier","created":"2025-12-01","cited_by_count":0,"area":null},{"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":"2601.20885","title":"What Hard Tokens Reveal: Exploiting Low-confidence Tokens for Membership Inference Attacks against Large Language Models","created":"2026-01-27","cited_by_count":0,"area":"safety"},{"id":"2602.13240","title":"AST-PAC: AST-guided Membership Inference for Code","created":"2026-01-30","cited_by_count":0,"area":"safety"},{"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":"2605.23448","title":"AI Security Research Should Better Incentivize Defense Research","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2607.10020","title":"FindMyText: Robust, Scalable Detection of Text Containment in Large Web-Crawled Corpora","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2608.02154","title":"Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints","created":"2026-08-03","cited_by_count":0,"area":"distill"},{"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":"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":"2609.25014","title":"Not All 4-bit Quantizers Are Equal: Deployment-Time Mitigation of PII Leakage in Fine-Tuned Small Language Models","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2610.03585","title":"Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.18486","title":"SoK: Rethinking Membership Inference in Tabular Machine Learning","created":"2026-10-13","cited_by_count":0,"area":"safety"},{"id":"2610.19114","title":"Genesis Steering: Better Activation Steering Through Training Data","created":"2026-10-13","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}