{"total":88,"rows":[{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387,"area":null},{"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":"2205.10770","title":"Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models","created":"2022-05-22","cited_by_count":220,"area":null},{"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":"2204.00032","title":"Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets","created":"2022-03-31","cited_by_count":101,"area":null},{"id":"2401.06059","title":"Investigating Data Contamination for Pre-training Language Models","created":"2024-01-11","cited_by_count":91,"area":null},{"id":"2402.09910","title":"DE-COP: Detecting Copyrighted Content in Language Models Training Data","created":"2024-02-15","cited_by_count":74,"area":null},{"id":"2308.16149","title":"Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models","created":"2023-08-30","cited_by_count":69,"area":null},{"id":"2312.03724","title":"DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer","created":"2023-11-27","cited_by_count":57,"area":null},{"id":"2310.10383","title":"Privacy in Large Language Models: Attacks, Defenses and Future Directions","created":"2023-10-16","cited_by_count":51,"area":null},{"id":"2205.12506","title":"Memorization in NLP Fine-tuning Methods","created":"2022-05-25","cited_by_count":45,"area":null},{"id":"2305.16157","title":"Training Data Extraction From Pre-trained Language Models: A Survey","created":"2023-05-25","cited_by_count":45,"area":null},{"id":"2401.04343","title":"Private Fine-tuning of Large Language Models with Zeroth-order Optimization","created":"2024-01-09","cited_by_count":41,"area":null},{"id":"2408.12787","title":"LLM-PBE: Assessing Data Privacy in Large Language Models","created":"2024-08-23","cited_by_count":41,"area":null},{"id":"2402.09363","title":"Copyright Traps for Large Language Models","created":"2024-02-14","cited_by_count":37,"area":null},{"id":"2307.04401","title":"Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation","created":"2023-07-10","cited_by_count":36,"area":null},{"id":"2310.09266","title":"User Inference Attacks on Large Language Models","created":"2023-10-13","cited_by_count":36,"area":null},{"id":"2404.06209","title":"Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models","created":"2024-04-09","cited_by_count":36,"area":null},{"id":"2305.09859","title":"Smaller Language Models are Better Black-box Machine-Generated Text Detectors","created":"2023-05-17","cited_by_count":35,"area":null},{"id":"2405.16281","title":"ConStat: Performance-Based Contamination Detection in Large Language Models","created":"2024-05-25","cited_by_count":33,"area":null},{"id":"2411.03923","title":"Evaluation data contamination in LLMs: how do we measure it and (when) does it matter?","created":"2024-11-06","cited_by_count":32,"area":null},{"id":"2310.01424","title":"Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey","created":"2023-09-27","cited_by_count":30,"area":null},{"id":"2402.02823","title":"Evading Data Contamination Detection for Language Models is (too) Easy","created":"2024-02-05","cited_by_count":30,"area":null},{"id":"2410.02650","title":"Undesirable Memorization in Large Language Models: A Survey","created":"2024-10-03","cited_by_count":29,"area":null},{"id":"2409.14457","title":"Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends","created":"2024-09-22","cited_by_count":26,"area":null},{"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":"2401.00676","title":"Digger: Detecting Copyright Content Mis-usage in Large Language Model Training","created":"2024-01-01","cited_by_count":25,"area":null},{"id":"2406.01333","title":"Probing Language Models for Pre-training Data Detection","created":"2024-06-03","cited_by_count":25,"area":null},{"id":"2405.11930","title":"Data Contamination Calibration for Black-box LLMs","created":"2024-05-20","cited_by_count":24,"area":null},{"id":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23,"area":null},{"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":"2305.15008","title":"Are Chatbots Ready for Privacy-Sensitive Applications? An Investigation into Input Regurgitation and Prompt-Induced Sanitization","created":"2023-05-24","cited_by_count":17,"area":null},{"id":"2506.02959","title":"HACo-Det: A Study Towards Fine-Grained Machine-Generated Text Detection under Human-AI Coauthoring","created":"2025-06-03","cited_by_count":15,"area":null},{"id":"2507.06969","title":"Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy","created":"2025-07-09","cited_by_count":15,"area":null},{"id":"2311.07682","title":"Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion","created":"2023-11-13","cited_by_count":13,"area":null},{"id":"2407.16607","title":"Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?","created":"2024-07-23","cited_by_count":13,"area":null},{"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":"2212.10520","title":"Privacy-Preserving Domain Adaptation of Semantic Parsers","created":"2022-12-20","cited_by_count":12,"area":null},{"id":"2309.16398","title":"Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey","created":"2023-09-28","cited_by_count":12,"area":null},{"id":"2311.11415","title":"A Security Risk Taxonomy for Prompt-Based Interaction With Large Language Models","created":"2023-11-19","cited_by_count":12,"area":null},{"id":"2407.21248","title":"Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens","created":"2024-07-30","cited_by_count":11,"area":null},{"id":"2310.16152","title":"Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering","created":"2023-10-24","cited_by_count":9,"area":null},{"id":"2310.13291","title":"Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks","created":"2023-10-20","cited_by_count":8,"area":null},{"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":"2406.11380","title":"Evaluating LLMs for Quotation Attribution in Literary Texts: A Case Study of LLaMa3","created":"2024-06-17","cited_by_count":8,"area":null},{"id":"2411.10670","title":"IntentGPT: Few-shot Intent Discovery with Large Language Models","created":"2024-11-16","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":"2503.12072","title":"Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models","created":"2025-03-15","cited_by_count":8,"area":null},{"id":"2502.05087","title":"Mitigating Unintended Memorization with LoRA in Federated Learning for LLMs","created":"2025-02-07","cited_by_count":7,"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":"2506.10024","title":"Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models","created":"2025-06-09","cited_by_count":7,"area":null},{"id":"2507.21198","title":"Uncovering Gradient Inversion Risks in Practical Language Model Training","created":"2025-07-28","cited_by_count":7,"area":null},{"id":"2305.07882","title":"Dual Use Concerns of Generative AI and Large Language Models","created":"2023-05-13","cited_by_count":6,"area":null},{"id":"2406.18326","title":"PaCoST: Paired Confidence Significance Testing for Benchmark Contamination Detection in Large Language Models","created":"2024-06-26","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":"2502.17259","title":"Detecting Benchmark Contamination Through Watermarking","created":"2025-02-24","cited_by_count":6,"area":null},{"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":"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":"2310.05553","title":"Regulation and NLP (RegNLP): Taming Large Language Models","created":"2023-10-09","cited_by_count":5,"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":"2305.14936","title":"Trade-Offs Between Fairness and Privacy in Language Modeling","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2406.14549","title":"Uncovering Latent Memories: Assessing Data Leakage and Memorization Patterns in Frontier AI Models","created":"2024-06-20","cited_by_count":4,"area":null},{"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":"2409.12367","title":"Extracting Memorized Training Data via Decomposition","created":"2024-09-18","cited_by_count":4,"area":null},{"id":"2410.12443","title":"Reconstruction of Differentially Private Text Sanitization via Large Language Models","created":"2024-10-16","cited_by_count":4,"area":null},{"id":"2601.07988","title":"From Word Sequences to Behavioral Sequences: Adapting Modeling and Evaluation Paradigms for Longitudinal NLP","created":"2026-01-12","cited_by_count":4,"area":null},{"id":"2407.11059","title":"Was it Slander? Towards Exact Inversion of Generative Language Models","created":"2024-07-10","cited_by_count":3,"area":null},{"id":"2509.14608","title":"Enterprise AI Must Enforce Participant-Aware Access Control","created":"2025-09-18","cited_by_count":3,"area":null},{"id":"2603.21078","title":"Assessing the Ability of Neural TTS Systems to Model Consonant-Induced F0 Perturbation","created":"2026-03-22","cited_by_count":3,"area":null},{"id":"2409.07415","title":"SoK: Security and Privacy Risks of Healthcare AI","created":"2024-09-11","cited_by_count":2,"area":null},{"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":"2509.12152","title":"Beyond PII: How Users Attempt to Estimate and Mitigate Implicit LLM Inference","created":"2025-09-15","cited_by_count":2,"area":null},{"id":"2602.15897","title":"Mitigating Gradient Inversion Risks in Language Models via Token Obfuscation","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2503.13872","title":"Empirical Calibration and Metric Differential Privacy in Language Models","created":"2025-03-18","cited_by_count":1,"area":null},{"id":"2507.00258","title":"Impact of Fine-Tuning Methods on Memorization in Large Language Models","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2509.10682","title":"LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2510.08813","title":"The Model's Language Matters: A Comparative Privacy Analysis of LLMs","created":"2025-10-09","cited_by_count":1,"area":null},{"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":"2601.19936","title":"Gap-K%: Measuring Top-1 Prediction Gap for Detecting Pretraining Data","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2603.08179","title":"Privacy-Preserving End-to-End Full-Duplex Speech Dialogue Models","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2605.06505","title":"PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.24420","title":"Batch Normalization Amplifies Memorization and Privacy Risks","created":"2026-05-23","cited_by_count":1,"area":null},{"id":"2402.01725","title":"Fortifying Ethical Boundaries in AI: Advanced Strategies for Enhancing Security in Large Language Models","created":"2024-01-27","cited_by_count":0,"area":null},{"id":"2408.11046","title":"Inside the Black Box: Detecting Data Leakage in Pre-trained Language Encoders","created":"2024-08-20","cited_by_count":0,"area":null},{"id":"2412.07796","title":"MRP-LLM: Multitask Reflective Large Language Models for Privacy-Preserving Next POI Recommendation","created":"2024-12-03","cited_by_count":0,"area":null},{"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":"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":"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}],"next_cursor":null}