{"total":64,"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":"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":"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":"2410.02650","title":"Undesirable Memorization in Large Language Models: A Survey","created":"2024-10-03","cited_by_count":29,"area":null},{"id":"2411.00154","title":"Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models","created":"2024-10-31","cited_by_count":24,"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":"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":"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":"2410.07582","title":"Detecting Training Data of Large Language Models via Expectation Maximization","created":"2024-10-10","cited_by_count":13,"area":"safety"},{"id":"2506.10424","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":"2509.16330","title":"Generalizability of Large Language Model-Based Agents: A Comprehensive Survey","created":"2025-09-19","cited_by_count":10,"area":"agents"},{"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":"2511.14045","title":"Auditing Data Membership in Reinforcement Learning With Verifiable Rewards","created":"2025-11-18","cited_by_count":8,"area":null},{"id":"2410.13088","title":"Self-Comparison for Dataset-Level Membership Inference in Large (Vision-)Language Models","created":"2024-10-16","cited_by_count":7,"area":"mllm"},{"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":"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":"2510.09259","title":"Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models","created":"2025-10-10","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":"2601.18110","title":"AttenMIA: LLM Membership Inference Attack through Attention Signals","created":"2026-01-26","cited_by_count":4,"area":"safety"},{"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":"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":"2601.11314","title":"Membership Inference on LLMs in the Wild","created":"2026-01-16","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":"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":"2510.19492","title":"Machine Text Detectors are Membership Inference Attacks","created":"2025-10-22","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":"2601.13607","title":"When Reasoning Leaks Membership: Membership Inference Attack on Black-box Large Reasoning Models","created":"2026-01-20","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":"2505.11837","title":"On Membership Inference Attacks in Knowledge Distillation","created":"2025-05-17","cited_by_count":1,"area":"safety"},{"id":"2506.14474","title":"LexiMark: Robust Watermarking via Lexical Substitutions to Enhance Membership Verification of an LLM's Textual Training Data","created":"2025-06-17","cited_by_count":1,"area":"safety"},{"id":"2510.09717","title":"Provable Training Data Identification for Large Language Models","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2510.24807","title":"Learning to Attack: Uncovering Privacy Risks in Sequential Data Releases","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2512.03100","title":"Ensemble Privacy Defense for Knowledge-Intensive LLMs against Membership Inference Attacks","created":"2025-12-01","cited_by_count":1,"area":"rag"},{"id":"2605.30348","title":"LLMSurgeon: Diagnosing Data Mixture of Large Language Models","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.17110","title":"Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMs","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2505.13249","title":"RN-F: A Novel Approach for Mitigating Contaminated Data in Large Language Models","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2507.15104","title":"AnalogFed: Privacy-Preserving Discovery of Analog Circuits at Scale with Federated Generative AI","created":"2025-07-20","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":"2510.10902","title":"Auditing Information Disclosure During Large-Scale Gradient-Based Training via Gradient Uniqueness","created":"2025-10-13","cited_by_count":0,"area":null},{"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":"2511.04228","title":"REMIND: Input Loss Landscapes Reveal Residual Memorization in Post-Unlearning LLMs","created":"2025-11-06","cited_by_count":0,"area":"safety"},{"id":"2511.15192","title":"As If We've Met Before: LLMs Exhibit Certainty in Recognizing Seen Files","created":"2025-11-19","cited_by_count":0,"area":null},{"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":"2601.06827","title":"PDR: A Plug-and-Play Positional Decay Framework for LLM Pre-training Data Detection","created":"2026-01-11","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":"2603.28942","title":"ReproMIA: A Comprehensive Analysis of Model Reprogramming for Proactive Membership Inference Attacks","created":"2026-03-30","cited_by_count":0,"area":"diffusion"},{"id":"2604.01904","title":"Combating Data Laundering in LLM Training","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.19561","title":"Detecting Data Contamination in Large Language Models","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.06423","title":"Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models","created":"2026-05-07","cited_by_count":0,"area":"safety"},{"id":"2605.21543","title":"Provable Joint Decontamination for Benchmarking Multiple Large Language Models","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.22373","title":"Boundary-targeted Membership Inference Attacks on Safety Classifiers","created":"2026-05-21","cited_by_count":0,"area":"safety"},{"id":"2605.29888","title":"LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"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":"2606.31991","title":"Anchored or Drifting: What Recursive Self-Generation Reveals About Training Data","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.16207","title":"JUMP: Single-Pass Membership Inference on Fine-Tuned Diffusion Language Models","created":"2026-05-09","cited_by_count":0,"area":"diffusion"},{"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":"2609.10611","title":"Black-Box Membership Inference via Word-Level Probability Estimation","created":"2026-09-08","cited_by_count":0,"area":"safety"},{"id":"2609.21888","title":"Detecting Pretraining Data in Large Language Models from a Free-Energy Perspective","created":"2026-09-18","cited_by_count":0,"area":null},{"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}