{"total":114,"rows":[{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387,"area":null},{"id":"2310.17623","title":"Proving Test Set Contamination in Black Box Language Models","created":"2023-10-26","cited_by_count":230,"area":null},{"id":"2409.00138","title":"PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action","created":"2024-08-29","cited_by_count":171,"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":"2401.06059","title":"Investigating Data Contamination for Pre-training Language Models","created":"2024-01-11","cited_by_count":91,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2409.14781","title":"Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method","created":"2024-09-23","cited_by_count":55,"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":"2403.12958","title":"Dated Data: Tracing Knowledge Cutoffs in Large Language Models","created":"2024-03-19","cited_by_count":51,"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":"2310.18362","title":"SoK: Memorization in General-Purpose Large Language Models","created":"2023-10-24","cited_by_count":37,"area":null},{"id":"2402.09363","title":"Copyright Traps for Large Language Models","created":"2024-02-14","cited_by_count":37,"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":"2405.16281","title":"ConStat: Performance-Based Contamination Detection in Large Language Models","created":"2024-05-25","cited_by_count":33,"area":null},{"id":"2307.08925","title":"Integration of Large Language Models and Federated Learning","created":"2023-07-18","cited_by_count":31,"area":null},{"id":"2403.19851","title":"Localizing Paragraph Memorization in Language Models","created":"2024-03-28","cited_by_count":31,"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":"2406.14644","title":"Unveiling the Spectrum of Data Contamination in Language Models: A Survey from Detection to Remediation","created":"2024-06-20","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":"2310.09639","title":"DPZero: Private Fine-Tuning of Language Models without Backpropagation","created":"2023-10-14","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":"2310.14369","title":"MoPe: Model Perturbation-based Privacy Attacks on Language Models","created":"2023-10-22","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":"2409.01790","title":"Training on the Benchmark Is Not All You Need","created":"2024-09-03","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":"2411.13405","title":"On the Way to LLM Personalization: Learning to Remember User Conversations","created":"2024-11-20","cited_by_count":21,"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":"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":"2403.06644","title":"Elephants Never Forget: Testing Language Models for Memorization of Tabular Data","created":"2024-03-11","cited_by_count":19,"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":"2504.19373","title":"Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models","created":"2025-04-27","cited_by_count":14,"area":null},{"id":"2404.07940","title":"InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models","created":"2024-03-11","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":"2309.17319","title":"Building Privacy-Preserving and Secure Geospatial Artificial Intelligence Foundation Models","created":"2023-09-29","cited_by_count":12,"area":null},{"id":"2411.05818","title":"Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives","created":"2024-11-02","cited_by_count":12,"area":null},{"id":"2503.14043","title":"Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions","created":"2025-03-18","cited_by_count":12,"area":null},{"id":"2402.17012","title":"Pandora's White-Box: Precise Training Data Detection and Extraction in Large Language Models","created":"2024-02-26","cited_by_count":11,"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":"2411.10023","title":"Model Inversion Attacks: A Survey of Approaches and Countermeasures","created":"2024-11-15","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":"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":"2405.14517","title":"TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models","created":"2024-05-23","cited_by_count":8,"area":null},{"id":"2407.02596","title":"Towards More Realistic Extraction Attacks: An Adversarial Perspective","created":"2024-07-02","cited_by_count":8,"area":null},{"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":"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":"2505.23799","title":"Estimating LLM Consistency: A User Baseline vs Surrogate Metrics","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2510.27055","title":"Detecting Data Contamination in LLMs via In-Context Learning","created":"2025-10-30","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":"2407.19262","title":"Understanding Memorisation in LLMs: Dynamics, Influencing Factors, and Implications","created":"2024-07-27","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":"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":"2503.07501","title":"Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond","created":"2025-03-10","cited_by_count":6,"area":null},{"id":"2506.08762","title":"EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements","created":"2025-06-10","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":"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":"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":"2407.04981","title":"TRACE: TRansformer-based Attribution using Contrastive Embeddings in LLMs","created":"2024-07-06","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":"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":"2503.20846","title":"Generating Synthetic Data with Formal Privacy Guarantees: State of the Art and the Road Ahead","created":"2025-03-26","cited_by_count":4,"area":null},{"id":"2506.00808","title":"Unlearning Inversion Attacks for Graph Neural Networks","created":"2025-06-01","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":"2406.05900","title":"Large Language Models Memorize Sensor Datasets! Implications on Human Activity Recognition Research","created":"2024-06-09","cited_by_count":3,"area":null},{"id":"2409.15868","title":"Privacy Evaluation Benchmarks for NLP Models","created":"2024-09-24","cited_by_count":3,"area":null},{"id":"2601.03791","title":"Do LLMs Really Memorize Personally Identifiable Information? Revisiting PII Leakage with a Cue-Controlled Memorization Framework","created":"2026-01-07","cited_by_count":3,"area":null},{"id":"2404.17143","title":"Quantifying Memorization and Detecting Training Data of Pre-trained Language Models using Japanese Newspaper","created":"2024-04-26","cited_by_count":2,"area":null},{"id":"2407.08152","title":"Privacy-Preserving Data Deduplication for Enhancing Federated Learning of Language Models (Extended Version)","created":"2024-07-11","cited_by_count":2,"area":null},{"id":"2411.10842","title":"CODECLEANER: Elevating Standards with A Robust Data Contamination Mitigation Toolkit","created":"2024-11-16","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":"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":"2601.04301","title":"Quantifying the Effect of Test Set Contamination on Generative Evaluations","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2605.19999","title":"LLM Benchmark Datasets Should Be Contamination-Resistant","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2411.07070","title":"On Active Privacy Auditing in Supervised Fine-tuning for White-Box Language Models","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2501.16671","title":"Data-Free Model-Related Attacks: Unleashing the Potential of Generative AI","created":"2025-01-28","cited_by_count":1,"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":"2504.05059","title":"MIAT: Maneuver-Intention-Aware Transformer for Spatio-Temporal Trajectory Prediction","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2505.23792","title":"Zero-Trust Foundation Models: A New Paradigm for Secure and Collaborative Artificial Intelligence for Internet of Things","created":"2025-05-26","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":"2507.06056","title":"Data Compressibility Quantifies LLM Memorization","created":"2025-07-08","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":"2510.09717","title":"Provable Training Data Identification for Large Language Models","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2511.07505","title":"FedRW: Efficient Privacy-Preserving Data Reweighting for Enhancing Federated Learning of Language Models","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2601.04895","title":"DVD: A Robust Method for Detecting Variant Contamination in Large Language Model Evaluation","created":"2026-01-08","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":"2407.15868","title":"A Survey on Differential Privacy for SpatioTemporal Data in Transportation Research","created":"2024-07-18","cited_by_count":0,"area":null},{"id":"2503.20800","title":"Evidencing Unauthorized Training Data from AI Generated Content using Information Isotopes","created":"2025-03-24","cited_by_count":0,"area":null},{"id":"2506.20481","title":"Counterfactual Influence as a Distributional Quantity","created":"2025-06-25","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":"2510.04033","title":"A global log for medical AI","created":"2025-10-05","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":"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}],"next_cursor":"100"}