{"total":878,"rows":[{"id":"2301.13188","title":"Extracting Training Data from Diffusion Models","created":"2023-01-30","cited_by_count":732,"area":"diffusion"},{"id":"2401.06121","title":"TOFU: A Task of Fictitious Unlearning for LLMs","created":"2024-01-11","cited_by_count":533,"area":"safety"},{"id":"2212.03860","title":"Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models","created":"2022-12-07","cited_by_count":424,"area":"diffusion"},{"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":"2310.12508","title":"SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation","created":"2023-10-19","cited_by_count":386,"area":"diffusion"},{"id":"2202.06539","title":"Deduplicating Training Data Mitigates Privacy Risks in Language Models","created":"2022-02-14","cited_by_count":314,"area":null},{"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":"2204.13650","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","created":"2022-04-28","cited_by_count":224,"area":null},{"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":"2112.12938","title":"Counterfactual Memorization in Neural Language Models","created":"2021-12-24","cited_by_count":156,"area":null},{"id":"2206.10469","title":"The Privacy Onion Effect: Memorization is Relative","created":"2022-06-21","cited_by_count":136,"area":null},{"id":"2302.01316","title":"Are Diffusion Models Vulnerable to Membership Inference Attacks?","created":"2023-02-02","cited_by_count":136,"area":"diffusion"},{"id":"2305.08846","title":"Privacy Auditing with One (1) Training Run","created":"2023-05-15","cited_by_count":123,"area":null},{"id":"2206.00240","title":"Privacy for Free: How does Dataset Condensation Help Privacy?","created":"2022-06-01","cited_by_count":120,"area":null},{"id":"2402.15159","title":"Machine Unlearning of Pre-trained Large Language Models","created":"2024-02-23","cited_by_count":119,"area":"safety"},{"id":"2207.00099","title":"Measuring Forgetting of Memorized Training Examples","created":"2022-06-30","cited_by_count":118,"area":null},{"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":"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":"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":"2407.21720","title":"Detecting, Explaining, and Mitigating Memorization in Diffusion Models","created":"2024-07-31","cited_by_count":95,"area":"diffusion"},{"id":"2404.15146","title":"Rethinking LLM Memorization through the Lens of Adversarial Compression","created":"2024-04-23","cited_by_count":94,"area":"lr"},{"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":"2302.03262","title":"Membership Inference Attacks against Diffusion Models","created":"2023-02-07","cited_by_count":86,"area":"diffusion"},{"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":"2305.15594","title":"Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models","created":"2023-05-24","cited_by_count":83,"area":null},{"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":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2403.01749","title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text","created":"2024-03-04","cited_by_count":76,"area":"synth"},{"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":"2406.16201","title":"Blind Baselines Beat Membership Inference Attacks for Foundation Models","created":"2024-06-23","cited_by_count":69,"area":"safety"},{"id":"2305.15560","title":"Differentially Private Synthetic Data via Foundation Model APIs 1: Images","created":"2023-05-24","cited_by_count":65,"area":null},{"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":"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":"2310.15007","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":"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":"2305.18355","title":"An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization","created":"2023-05-26","cited_by_count":54,"area":"diffusion"},{"id":"2212.01539","title":"Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping","created":"2022-12-03","cited_by_count":52,"area":null},{"id":"2212.10986","title":"SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning","created":"2022-12-21","cited_by_count":51,"area":null},{"id":"2302.09923","title":"Prompt Stealing Attacks Against Text-to-Image Generation Models","created":"2023-02-20","cited_by_count":51,"area":null},{"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":"2301.09956","title":"Membership Inference of Diffusion Models","created":"2023-01-24","cited_by_count":46,"area":"diffusion"},{"id":"2302.07225","title":"Bounding Training Data Reconstruction in DP-SGD","created":"2023-02-14","cited_by_count":46,"area":"safety"},{"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":"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":"2405.20446","title":"Is My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented Generation","created":"2024-05-30","cited_by_count":44,"area":"rag"},{"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":"2308.06405","title":"White-box Membership Inference Attacks against Diffusion Models","created":"2023-08-11","cited_by_count":42,"area":"diffusion"},{"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":"2306.12983","title":"Towards More Realistic Membership Inference Attacks on Large Diffusion Models","created":"2023-06-22","cited_by_count":41,"area":"diffusion"},{"id":"2408.12787","title":"LLM-PBE: Assessing Data Privacy in Large Language Models","created":"2024-08-23","cited_by_count":41,"area":null},{"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":"2309.05610","title":"Privacy Side Channels in Machine Learning Systems","created":"2023-09-11","cited_by_count":40,"area":null},{"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":"2405.14800","title":"Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy","created":"2024-05-23","cited_by_count":38,"area":"diffusion"},{"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":"2402.09363","title":"Copyright Traps for Large Language Models","created":"2024-02-14","cited_by_count":37,"area":null},{"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":"2302.03098","title":"One-shot Empirical Privacy Estimation for Federated Learning","created":"2023-02-06","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":"2310.10402","title":"Real-Fake: Effective Training Data Synthesis Through Distribution Matching","created":"2023-10-16","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":"2404.17399","title":"Evaluations of Machine Learning Privacy Defenses are Misleading","created":"2024-04-26","cited_by_count":36,"area":null},{"id":"2312.08207","title":"Black-box Membership Inference Attacks against Fine-tuned Diffusion Models","created":"2023-12-13","cited_by_count":35,"area":"diffusion"},{"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":"2411.02902","title":"Membership Inference Attacks against Large Vision-Language Models","created":"2024-11-05","cited_by_count":33,"area":"mllm"},{"id":"2202.07623","title":"Defending against Reconstruction Attacks with R\\'enyi Differential Privacy","created":"2022-02-15","cited_by_count":32,"area":null},{"id":"2211.05427","title":"On the Privacy Risks of Algorithmic Recourse","created":"2022-11-10","cited_by_count":32,"area":"safety"},{"id":"2403.00871","title":"Teach LLMs to Phish: Stealing Private Information from Language Models","created":"2024-03-01","cited_by_count":32,"area":null},{"id":"2408.03400","title":"Attacks and Defenses for Generative Diffusion Models: A Comprehensive Survey","created":"2024-08-06","cited_by_count":32,"area":"diffusion"},{"id":"2411.10512","title":"On the Privacy Risk of In-context Learning","created":"2024-11-15","cited_by_count":32,"area":"safety"},{"id":"2208.12348","title":"SNAP: Efficient Extraction of Private Properties with Poisoning","created":"2022-08-25","cited_by_count":31,"area":null},{"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":"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}],"next_cursor":"100"}