{"total":98,"rows":[{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387,"area":null},{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205,"area":"agents"},{"id":"2402.07841","title":"Do Membership Inference Attacks Work on Large Language Models?","created":"2024-02-12","cited_by_count":195,"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":"2407.19354","title":"The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies","created":"2024-07-28","cited_by_count":131,"area":"agents"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2404.02936","title":"Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models","created":"2024-04-03","cited_by_count":103,"area":null},{"id":"2406.15968","title":"ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods","created":"2024-06-23","cited_by_count":64,"area":"safety"},{"id":"2403.12958","title":"Dated Data: Tracing Knowledge Cutoffs in Large Language Models","created":"2024-03-19","cited_by_count":51,"area":null},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2409.01380","title":"Membership Inference Attacks Against In-Context Learning","created":"2024-09-02","cited_by_count":43,"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":"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":"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":"2411.02902","title":"Membership Inference Attacks against Large Vision-Language Models","created":"2024-11-05","cited_by_count":33,"area":"mllm"},{"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":"2410.14479","title":"Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models","created":"2024-10-18","cited_by_count":22,"area":"rag"},{"id":"2505.01976","title":"A Survey on Privacy Risks and Protection in Large Language Models","created":"2025-05-04","cited_by_count":21,"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":"2408.08661","title":"MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector","created":"2024-08-16","cited_by_count":15,"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":"2506.11680","title":"Malicious LLM-Based Conversational AI Makes Users Reveal Personal Information","created":"2025-06-13","cited_by_count":13,"area":null},{"id":"2404.00699","title":"A Comprehensive Survey of Contamination Detection Methods in Large Language Models","created":"2024-03-31","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":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2410.11182","title":"A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality","created":"2024-10-15","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":"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":"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":"2403.16139","title":"A Little Leak Will Sink a Great Ship: Survey of Transparency for Large Language Models from Start to Finish","created":"2024-03-24","cited_by_count":6,"area":null},{"id":"2409.03274","title":"Recent Advances in Attack and Defense Approaches of Large Language Models","created":"2024-09-05","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":"2502.13313","title":"Revisiting Privacy, Utility, and Efficiency Trade-offs when Fine-Tuning Large Language Models","created":"2025-02-18","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":"2409.12367","title":"Extracting Memorized Training Data via Decomposition","created":"2024-09-18","cited_by_count":4,"area":null},{"id":"2502.11533","title":"Be Cautious When Merging Unfamiliar LLMs: A Phishing Model Capable of Stealing Privacy","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2504.21036","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","created":"2025-04-28","cited_by_count":4,"area":null},{"id":"2507.16124","title":"Benchmarking LLM Privacy Recognition for Social Robot Decision Making","created":"2025-07-22","cited_by_count":4,"area":null},{"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":"2512.16059","title":"ContextLeak: Auditing Leakage in Private In-Context Learning Methods","created":"2025-12-18","cited_by_count":4,"area":null},{"id":"2409.15868","title":"Privacy Evaluation Benchmarks for NLP Models","created":"2024-09-24","cited_by_count":3,"area":null},{"id":"2503.01208","title":"Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models","created":"2025-03-03","cited_by_count":3,"area":"mllm"},{"id":"2506.04453","title":"Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2508.07054","title":"Membership and Memorization in LLM Knowledge Distillation","created":"2025-08-09","cited_by_count":3,"area":"distill"},{"id":"2509.14608","title":"Enterprise AI Must Enforce Participant-Aware Access Control","created":"2025-09-18","cited_by_count":3,"area":null},{"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":"2405.08134","title":"Many-Shot Regurgitation (MSR) Prompting","created":"2024-05-13","cited_by_count":2,"area":"safety"},{"id":"2411.15831","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2412.20087","title":"On the Validity of Traditional Vulnerability Scoring Systems for Adversarial Attacks against LLMs","created":"2024-12-28","cited_by_count":2,"area":null},{"id":"2503.07482","title":"How does Bayesian Sampling help Membership Inference Attacks?","created":"2025-03-10","cited_by_count":2,"area":"safety"},{"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":"2510.00125","title":"Direct Token Optimization: A Self-contained Approach to Large Language Model Unlearning","created":"2025-09-30","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":"2605.27825","title":"MRMMIA: Membership Inference Attacks on Memory in Chat Agents","created":"2026-05-27","cited_by_count":2,"area":"safety"},{"id":"2405.15140","title":"Better Membership Inference Privacy Measurement through Discrepancy","created":"2024-05-24","cited_by_count":1,"area":"safety"},{"id":"2410.18824","title":"PSY: Posterior Sampling Based Privacy Enhancer in Large Language Models","created":"2024-10-24","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":"2507.01752","title":"Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training","created":"2025-07-02","cited_by_count":1,"area":"safety"},{"id":"2509.02411","title":"A Survey: Towards Privacy and Security in Mobile Large Language Models","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2510.09717","title":"Provable Training Data Identification for Large Language Models","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2510.18674","title":"Exploring Membership Inference Vulnerabilities in Clinical Large Language Models","created":"2025-10-21","cited_by_count":1,"area":"safety"},{"id":"2511.11914","title":"Forgetting-MarI: LLM Unlearning via Marginal Information Regularization","created":"2025-11-14","cited_by_count":1,"area":"safety"},{"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":"2601.12104","title":"Powerful Training-Free Membership Inference Against Autoregressive Language Models","created":"2026-01-17","cited_by_count":1,"area":"safety"},{"id":"2602.01126","title":"WinFLoRA: Incentivizing Client-Adaptive Aggregation in Federated LoRA under Privacy Heterogeneity","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2602.08617","title":"ERIS: Enhancing the Privacy-Utility-Scalability Trade-Off in Federated Learning via Federated Shard Aggregation","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2603.24518","title":"TuneShift-KD: Knowledge Distillation and Transfer for Fine-tuned Models","created":"2026-03-25","cited_by_count":1,"area":"distill"},{"id":"2603.28605","title":"Unsafe2Safe: Controllable Image Anonymization for Downstream Utility","created":"2026-03-30","cited_by_count":1,"area":null},{"id":"2605.26133","title":"Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications","created":"2026-05-21","cited_by_count":1,"area":"safety"},{"id":"2607.01686","title":"WARP: Weight-Space Analysis for Recovering Training Data Portfolios","created":"2026-07-02","cited_by_count":1,"area":"safety"},{"id":"2505.03490","title":"A new membership inference attack that spots memorization in generative and predictive models: Loss-Based with Reference Model algorithm (LBRM)","created":"2025-05-06","cited_by_count":0,"area":"safety"},{"id":"2505.13819","title":"Fragments to Facts: Partial-Information Fragment Inference from LLMs","created":"2025-05-20","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":"2512.02786","title":"FiMMIA: scaling semantic perturbation-based membership inference across modalities","created":"2025-12-02","cited_by_count":0,"area":"safety"},{"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":"2512.15468","title":"How Do Semantically Equivalent Code Transformations Impact Membership Inference on LLMs for Code?","created":"2025-12-17","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":"2601.21628","title":"Noise as a Probe: Membership Inference Attacks on Diffusion Models Leveraging Initial Noise","created":"2026-01-29","cited_by_count":0,"area":"diffusion"},{"id":"2601.22935","title":"Protecting Private Code in IDE Autocomplete using Differential Privacy","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.00688","title":"Provably Protecting Fine-Tuned LLMs from Training Data Extraction while Preserving Utility","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2603.13570","title":"Privacy-Preserving Machine Learning for IoT: A Cross-Paradigm Survey and Future Roadmap","created":"2026-03-13","cited_by_count":0,"area":null},{"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":"2603.22987","title":"A Critical Review on the Effectiveness and Privacy Threats of Membership Inference Attacks","created":"2026-03-24","cited_by_count":0,"area":"safety"},{"id":"2604.22191","title":"Behavioral Canaries: Auditing Private Retrieved Context Usage in RL Fine-Tuning","created":"2026-04-24","cited_by_count":0,"area":"agents"},{"id":"2605.07088","title":"Membership Inference Attacks on Vision-Language-Action Models","created":"2026-05-08","cited_by_count":0,"area":"safety"},{"id":"2605.12264","title":"Reconstruction of Personally Identifiable Information from Proprietary Data in Supervised Fine-Tuned Models","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.17341","title":"Single-Sample Black-Box Membership Inference Attack against Vision-Language Models via Cross-modal Semantic Alignment","created":"2026-05-17","cited_by_count":0,"area":"mllm"},{"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":"2608.00144","title":"Leak It: Per-Document Extraction Beyond Aggregate Membership Inference","created":"2026-07-31","cited_by_count":0,"area":"safety"},{"id":"2609.00873","title":"Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry","created":"2026-09-01","cited_by_count":0,"area":"diffusion"},{"id":"2609.33898","title":"No Free Efficiency: Revisiting the Trade-off Between Training Efficiency and Model Vulnerability","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.06236","title":"DP-ES: Differentially Private Evolution Strategies for Prompt Optimization","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.11423","title":"Policy Alignment: New Signals for Membership Auditing in On-Policy Distillation","created":"2026-10-08","cited_by_count":0,"area":"distill"},{"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"},{"id":"2610.17904","title":"Stable-Plastic Subspace Construction for Differentially Private Continual LoRA","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}