{"total":357,"rows":[{"id":"2401.06121","title":"TOFU: A Task of Fictitious Unlearning for LLMs","created":"2024-01-11","cited_by_count":533,"area":"safety"},{"id":"2302.00539","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","created":"2023-02-01","cited_by_count":285,"area":"safety"},{"id":"2302.09880","title":"Towards Unbounded Machine Unlearning","created":"2023-02-20","cited_by_count":268,"area":"safety"},{"id":"2305.18462","title":"Membership Inference Attacks against Language Models via Neighbourhood Comparison","created":"2023-05-29","cited_by_count":258,"area":"safety"},{"id":"2310.07579","title":"In-Context Unlearning: Language Models as Few Shot Unlearners","created":"2023-10-11","cited_by_count":224,"area":"safety"},{"id":"2402.07841","title":"Do Membership Inference Attacks Work on Large Language Models?","created":"2024-02-12","cited_by_count":195,"area":"safety"},{"id":"2203.03929","title":"Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks","created":"2022-03-08","cited_by_count":175,"area":"safety"},{"id":"2402.15159","title":"Machine Unlearning of Pre-trained Large Language Models","created":"2024-02-23","cited_by_count":119,"area":"safety"},{"id":"2406.06443","title":"LLM Dataset Inference: Did you train on my dataset?","created":"2024-06-10","cited_by_count":110,"area":"safety"},{"id":"2312.03262","title":"Low-Cost High-Power Membership Inference Attacks","created":"2023-12-06","cited_by_count":107,"area":"safety"},{"id":"2208.14933","title":"Membership Inference Attacks by Exploiting Loss Trajectory","created":"2022-08-31","cited_by_count":101,"area":"safety"},{"id":"2311.06062","title":"Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration","created":"2023-11-10","cited_by_count":98,"area":"safety"},{"id":"2403.03329","title":"Guardrail Baselines for Unlearning in LLMs","created":"2024-03-05","cited_by_count":96,"area":"safety"},{"id":"2402.19361","title":"Watermark Stealing in Large Language Models","created":"2024-02-29","cited_by_count":92,"area":"safety"},{"id":"2406.01257","title":"What makes unlearning hard and what to do about it","created":"2024-06-03","cited_by_count":89,"area":"safety"},{"id":"2402.15570","title":"Fast Adversarial Attacks on Language Models In One GPU Minute","created":"2024-02-23","cited_by_count":88,"area":"safety"},{"id":"2403.17336","title":"Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models","created":"2024-03-26","cited_by_count":86,"area":"safety"},{"id":"2403.01218","title":"Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy","created":"2024-03-02","cited_by_count":82,"area":"safety"},{"id":"2406.16201","title":"Blind Baselines Beat Membership Inference Attacks for Foundation Models","created":"2024-06-23","cited_by_count":69,"area":"safety"},{"id":"2307.03694","title":"Scalable Membership Inference Attacks via Quantile Regression","created":"2023-07-07","cited_by_count":65,"area":"safety"},{"id":"2406.15968","title":"ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods","created":"2024-06-23","cited_by_count":64,"area":"safety"},{"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":"2402.14904","title":"Watermarking Makes Language Models Radioactive","created":"2024-02-22","cited_by_count":58,"area":"safety"},{"id":"2310.15007","title":"Did the Neurons Read your Book? Document-level Membership Inference for Large Language Models","created":"2023-10-23","cited_by_count":56,"area":"safety"},{"id":"2406.09073","title":"Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition","created":"2024-06-13","cited_by_count":50,"area":"safety"},{"id":"2409.19798","title":"Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data","created":"2024-09-29","cited_by_count":50,"area":"safety"},{"id":"2404.03233","title":"Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning","created":"2024-04-04","cited_by_count":48,"area":"safety"},{"id":"2302.07225","title":"Bounding Training Data Reconstruction in DP-SGD","created":"2023-02-14","cited_by_count":46,"area":"safety"},{"id":"2409.19732","title":"Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement","created":"2024-09-29","cited_by_count":45,"area":"safety"},{"id":"2403.07362","title":"Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning","created":"2024-03-12","cited_by_count":44,"area":"safety"},{"id":"2405.03097","title":"To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models","created":"2024-05-06","cited_by_count":43,"area":"safety"},{"id":"2409.01380","title":"Membership Inference Attacks Against In-Context Learning","created":"2024-09-02","cited_by_count":43,"area":"safety"},{"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":"2210.10750","title":"Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries","created":"2022-10-19","cited_by_count":40,"area":"safety"},{"id":"2402.10892","title":"Proving membership in LLM pretraining data via data watermarks","created":"2024-02-16","cited_by_count":40,"area":"safety"},{"id":"2410.18057","title":"CLEAR: Character Unlearning in Textual and Visual Modalities","created":"2024-10-23","cited_by_count":39,"area":"safety"},{"id":"2310.00108","title":"Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study","created":"2023-09-29","cited_by_count":38,"area":"safety"},{"id":"2312.04095","title":"Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection","created":"2023-12-07","cited_by_count":37,"area":"safety"},{"id":"2406.17216","title":"Machine Unlearning Fails to Remove Data Poisoning Attacks","created":"2024-06-25","cited_by_count":37,"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":"2209.06997","title":"M^4I: Multi-modal Models Membership Inference","created":"2022-09-15","cited_by_count":34,"area":"safety"},{"id":"2211.00463","title":"Amplifying Membership Exposure via Data Poisoning","created":"2022-11-01","cited_by_count":34,"area":"safety"},{"id":"2309.08230","title":"A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Services","created":"2023-09-15","cited_by_count":34,"area":"safety"},{"id":"2206.05199","title":"Bayesian Estimation of Differential Privacy","created":"2022-06-10","cited_by_count":33,"area":"safety"},{"id":"2303.03446","title":"Students Parrot Their Teachers: Membership Inference on Model Distillation","created":"2023-03-06","cited_by_count":33,"area":"safety"},{"id":"2211.05427","title":"On the Privacy Risks of Algorithmic Recourse","created":"2022-11-10","cited_by_count":32,"area":"safety"},{"id":"2411.10512","title":"On the Privacy Risk of In-context Learning","created":"2024-11-15","cited_by_count":32,"area":"safety"},{"id":"2412.06157","title":"Membership Inference Attacks and Defenses in Federated Learning: A Survey","created":"2024-12-09","cited_by_count":31,"area":"safety"},{"id":"2307.01610","title":"Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction","created":"2023-07-04","cited_by_count":29,"area":"safety"},{"id":"2312.11658","title":"Traces of Memorisation in Large Language Models for Code","created":"2023-12-18","cited_by_count":29,"area":"safety"},{"id":"2405.20272","title":"Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable","created":"2024-05-30","cited_by_count":25,"area":"safety"},{"id":"2403.09562","title":"PreCurious: How Innocent Pre-Trained Language Models Turn into Privacy Traps","created":"2024-03-14","cited_by_count":23,"area":"safety"},{"id":"2407.15098","title":"SeqMIA: Sequential-Metric Based Membership Inference Attack","created":"2024-07-21","cited_by_count":23,"area":"safety"},{"id":"2503.06808","title":"Privacy Auditing of Large Language Models","created":"2025-03-09","cited_by_count":23,"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":"2306.07273","title":"Gaussian Membership Inference Privacy","created":"2023-06-12","cited_by_count":21,"area":"safety"},{"id":"2406.16565","title":"Noisy Neighbors: Efficient membership inference attacks against LLMs","created":"2024-06-24","cited_by_count":21,"area":"safety"},{"id":"2409.00426","title":"Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks","created":"2024-08-31","cited_by_count":21,"area":"safety"},{"id":"2205.13680","title":"Membership Inference Attack Using Self Influence Functions","created":"2022-05-26","cited_by_count":20,"area":"safety"},{"id":"2204.06106","title":"Optimal Membership Inference Bounds for Adaptive Composition of Sampled Gaussian Mechanisms","created":"2022-04-12","cited_by_count":19,"area":"safety"},{"id":"2205.14055","title":"A Blessing of Dimensionality in Membership Inference through Regularization","created":"2022-05-27","cited_by_count":18,"area":"safety"},{"id":"2307.01701","title":"Synthetic is all you need: removing the auxiliary data assumption for membership inference attacks against synthetic data","created":"2023-07-04","cited_by_count":18,"area":"safety"},{"id":"2407.17417","title":"Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?","created":"2024-07-24","cited_by_count":18,"area":"safety"},{"id":"2410.23232","title":"Attribute-to-Delete: Machine Unlearning via Datamodel Matching","created":"2024-10-30","cited_by_count":18,"area":"safety"},{"id":"2302.12685","title":"Active Membership Inference Attack under Local Differential Privacy in Federated Learning","created":"2023-02-24","cited_by_count":17,"area":"safety"},{"id":"2402.09477","title":"PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining","created":"2024-02-12","cited_by_count":17,"area":"safety"},{"id":"2402.01401","title":"An Information Theoretic Approach to Machine Unlearning","created":"2024-02-02","cited_by_count":16,"area":"safety"},{"id":"2406.07687","title":"Adversarial Machine Unlearning","created":"2024-06-11","cited_by_count":16,"area":"safety"},{"id":"2410.03537","title":"Ward: Provable RAG Dataset Inference via LLM Watermarks","created":"2024-10-04","cited_by_count":16,"area":"safety"},{"id":"2202.12232","title":"Bounding Membership Inference","created":"2022-02-24","cited_by_count":15,"area":"safety"},{"id":"2401.10458","title":"Contrastive Unlearning: A Contrastive Approach to Machine Unlearning","created":"2024-01-19","cited_by_count":15,"area":"safety"},{"id":"2601.18076","title":"Comparison requires valid measurement: Rethinking attack success rate comparisons in AI red teaming","created":"2026-01-26","cited_by_count":15,"area":"safety"},{"id":"2202.01243","title":"Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inference","created":"2022-02-02","cited_by_count":14,"area":"safety"},{"id":"2309.07983","title":"SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems","created":"2023-09-14","cited_by_count":14,"area":"safety"},{"id":"2310.11397","title":"Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning","created":"2023-10-17","cited_by_count":14,"area":"safety"},{"id":"2402.00179","title":"De-identification is not enough: a comparison between de-identified and synthetic clinical notes","created":"2024-01-31","cited_by_count":14,"area":"safety"},{"id":"2312.02052","title":"DUCK: Distance-based Unlearning via Centroid Kinematics","created":"2023-12-04","cited_by_count":13,"area":"safety"},{"id":"2402.09225","title":"Is My Data in Your AI? Membership Inference Test (MINT) applied to Face Biometrics","created":"2024-02-14","cited_by_count":13,"area":"safety"},{"id":"2402.15109","title":"Remaining-data-free Machine Unlearning by Suppressing Sample Contribution","created":"2024-02-23","cited_by_count":13,"area":"safety"},{"id":"2403.02116","title":"Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attacks","created":"2024-03-04","cited_by_count":13,"area":"safety"},{"id":"2405.16978","title":"OSLO: One-Shot Label-Only Membership Inference Attacks","created":"2024-05-27","cited_by_count":13,"area":"safety"},{"id":"2406.13348","title":"Textual Unlearning Gives a False Sense of Unlearning","created":"2024-06-19","cited_by_count":13,"area":"safety"},{"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":"2302.06676","title":"Netflix and Forget: Efficient and Exact Machine Unlearning from Bi-linear Recommendations","created":"2023-02-13","cited_by_count":12,"area":"safety"},{"id":"2311.00919","title":"MIST: Defending Against Membership Inference Attacks Through Membership-Invariant Subspace Training","created":"2023-11-02","cited_by_count":12,"area":"safety"},{"id":"2402.06289","title":"FedMIA: An Effective Membership Inference Attack Exploiting \"All for One\" Principle in Federated Learning","created":"2024-02-09","cited_by_count":12,"area":"safety"},{"id":"2408.00376","title":"On the Limitations and Prospects of Machine Unlearning for Generative AI","created":"2024-08-01","cited_by_count":12,"area":"safety"},{"id":"2408.05131","title":"Range Membership Inference Attacks","created":"2024-08-09","cited_by_count":12,"area":"safety"},{"id":"2306.15744","title":"Ticketed Learning-Unlearning Schemes","created":"2023-06-27","cited_by_count":11,"area":"safety"},{"id":"2403.08481","title":"SoK: Reducing the Vulnerability of Fine-tuned Language Models to Membership Inference Attacks","created":"2024-03-13","cited_by_count":11,"area":"safety"},{"id":"2405.15495","title":"Towards Natural Machine Unlearning","created":"2024-05-24","cited_by_count":11,"area":"safety"},{"id":"2405.17878","title":"An Information Theoretic Evaluation Metric For Strong Unlearning","created":"2024-05-28","cited_by_count":11,"area":"safety"},{"id":"2505.01524","title":"The DCR Delusion: Measuring the Privacy Risk of Synthetic Data","created":"2025-05-02","cited_by_count":11,"area":"safety"},{"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":"2207.12535","title":"Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning","created":"2022-07-25","cited_by_count":10,"area":"safety"},{"id":"2406.11544","title":"Do Parameters Reveal More than Loss for Membership Inference?","created":"2024-06-17","cited_by_count":10,"area":"safety"},{"id":"2411.19876","title":"LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states","created":"2024-11-29","cited_by_count":10,"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":"2405.19211","title":"Gone but Not Forgotten: Improved Benchmarks for Machine Unlearning","created":"2024-05-29","cited_by_count":9,"area":"safety"},{"id":"2406.07698","title":"Label Smoothing Improves Machine Unlearning","created":"2024-06-11","cited_by_count":9,"area":"safety"}],"next_cursor":"100"}