{"total":136,"rows":[{"id":"2210.01504","title":"Knowledge Unlearning for Mitigating Privacy Risks in Language Models","created":"2022-10-04","cited_by_count":437,"area":"safety"},{"id":"2308.14761","title":"Unified Concept Editing in Diffusion Models","created":"2023-08-25","cited_by_count":388,"area":"diffusion"},{"id":"2403.06135","title":"MACE: Mass Concept Erasure in Diffusion Models","created":"2024-03-10","cited_by_count":307,"area":"diffusion"},{"id":"2305.18462","title":"Membership Inference Attacks against Language Models via Neighbourhood Comparison","created":"2023-05-29","cited_by_count":258,"area":"safety"},{"id":"2311.17717","title":"Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers","created":"2023-11-29","cited_by_count":120,"area":"diffusion"},{"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":"2308.07061","title":"Machine Unlearning: Solutions and Challenges","created":"2023-08-14","cited_by_count":93,"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":"2502.06453","title":"MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations","created":"2025-02-10","cited_by_count":89,"area":"lr"},{"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":"2410.02879","title":"Position: LLM Unlearning Benchmarks are Weak Measures of Progress","created":"2024-10-03","cited_by_count":63,"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":"2403.11052","title":"Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention","created":"2024-03-17","cited_by_count":58,"area":"diffusion"},{"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":"2212.10717","title":"Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks","created":"2022-12-21","cited_by_count":43,"area":"safety"},{"id":"2408.16807","title":"STEREO: A Two-Stage Framework for Adversarially Robust Concept Erasing from Text-to-Image Diffusion Models","created":"2024-08-29","cited_by_count":42,"area":"diffusion"},{"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":"2402.09363","title":"Copyright Traps for Large Language Models","created":"2024-02-14","cited_by_count":37,"area":null},{"id":"2406.02366","title":"Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models","created":"2024-06-04","cited_by_count":37,"area":"diffusion"},{"id":"2406.17216","title":"Machine Unlearning Fails to Remove Data Poisoning Attacks","created":"2024-06-25","cited_by_count":37,"area":"safety"},{"id":"2404.17399","title":"Evaluations of Machine Learning Privacy Defenses are Misleading","created":"2024-04-26","cited_by_count":36,"area":null},{"id":"2303.03446","title":"Students Parrot Their Teachers: Membership Inference on Model Distillation","created":"2023-03-06","cited_by_count":33,"area":"safety"},{"id":"2210.08196","title":"Deep Regression Unlearning","created":"2022-10-15","cited_by_count":32,"area":"safety"},{"id":"2406.17746","title":"Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon","created":"2024-06-25","cited_by_count":31,"area":null},{"id":"2312.11658","title":"Traces of Memorisation in Large Language Models for Code","created":"2023-12-18","cited_by_count":29,"area":"safety"},{"id":"2306.10308","title":"Achilles' Heels: Vulnerable Record Identification in Synthetic Data Publishing","created":"2023-06-17","cited_by_count":28,"area":null},{"id":"2505.12677","title":"CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models","created":"2025-05-19","cited_by_count":27,"area":"diffusion"},{"id":"2503.06808","title":"Privacy Auditing of Large Language Models","created":"2025-03-09","cited_by_count":23,"area":"safety"},{"id":"2401.12233","title":"Memorization in Self-Supervised Learning Improves Downstream Generalization","created":"2024-01-19","cited_by_count":18,"area":null},{"id":"2403.10557","title":"Second-Order Information Matters: Revisiting Machine Unlearning for Large Language Models","created":"2024-03-13","cited_by_count":18,"area":"safety"},{"id":"2502.14921","title":"The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text","created":"2025-02-19","cited_by_count":18,"area":"synth"},{"id":"2405.19524","title":"AI Risk Management Should Incorporate Both Safety and Security","created":"2024-05-29","cited_by_count":17,"area":null},{"id":"2406.10218","title":"Semantic Membership Inference Attack against Large Language Models","created":"2024-06-14","cited_by_count":17,"area":"safety"},{"id":"2410.09591","title":"Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy","created":"2024-10-12","cited_by_count":17,"area":"safety"},{"id":"2307.10476","title":"What can we learn from Data Leakage and Unlearning for Law?","created":"2023-07-19","cited_by_count":15,"area":"safety"},{"id":"2404.05779","title":"Data Readiness for AI: A 360-Degree Survey","created":"2024-04-08","cited_by_count":15,"area":null},{"id":"2406.03880","title":"Memorization in deep learning: A survey","created":"2024-06-06","cited_by_count":15,"area":null},{"id":"2410.08074","title":"Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models","created":"2024-10-10","cited_by_count":15,"area":"diffusion"},{"id":"2503.13503","title":"SciHorizon: Benchmarking AI-for-Science Readiness from Scientific Data to Large Language Models","created":"2025-03-12","cited_by_count":15,"area":null},{"id":"2302.01428","title":"Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation","created":"2023-02-02","cited_by_count":14,"area":null},{"id":"2402.15109","title":"Remaining-data-free Machine Unlearning by Suppressing Sample Contribution","created":"2024-02-23","cited_by_count":13,"area":"safety"},{"id":"2406.18566","title":"Memorized Images in Diffusion Models share a Subspace that can be Located and Deleted","created":"2024-06-01","cited_by_count":13,"area":"diffusion"},{"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":"2208.13893","title":"Data Isotopes for Data Provenance in DNNs","created":"2022-08-29","cited_by_count":11,"area":null},{"id":"2306.15744","title":"Ticketed Learning-Unlearning Schemes","created":"2023-06-27","cited_by_count":11,"area":"safety"},{"id":"2307.00310","title":"Gradients Look Alike: Sensitivity is Often Overestimated in DP-SGD","created":"2023-07-01","cited_by_count":11,"area":null},{"id":"2411.01583","title":"Trustworthy Federated Learning: Privacy, Security, and Beyond","created":"2024-11-03","cited_by_count":11,"area":null},{"id":"2310.10604","title":"Generation or Replication: Auscultating Audio Latent Diffusion Models","created":"2023-10-16","cited_by_count":10,"area":"diffusion"},{"id":"2406.19256","title":"AI Data Readiness Inspector (AIDRIN) for Quantitative Assessment of Data Readiness for AI","created":"2024-06-27","cited_by_count":9,"area":null},{"id":"2409.19069","title":"Localizing Memorization in SSL Vision Encoders","created":"2024-09-27","cited_by_count":9,"area":null},{"id":"2506.13009","title":"Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective","created":"2025-06-16","cited_by_count":9,"area":"safety"},{"id":"2210.11049","title":"How Does a Deep Learning Model Architecture Impact Its Privacy? A Comprehensive Study of Privacy Attacks on CNNs and Transformers","created":"2022-10-20","cited_by_count":8,"area":null},{"id":"2305.18497","title":"Collaborative Learning via Prediction Consensus","created":"2023-05-29","cited_by_count":8,"area":null},{"id":"2403.14772","title":"Improving Robustness to Model Inversion Attacks via Sparse Coding Architectures","created":"2024-03-21","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":"2509.26598","title":"Are Robust LLM Fingerprints Adversarially Robust?","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2411.05743","title":"Free Record-Level Privacy Risk Evaluation Through Artifact-Based Methods","created":"2024-11-08","cited_by_count":7,"area":"safety"},{"id":"2412.12836","title":"A Survey on Recommendation Unlearning: Fundamentals, Taxonomy, Evaluation, and Open Questions","created":"2024-12-17","cited_by_count":7,"area":null},{"id":"2501.16614","title":"FUNU: Boosting Machine Unlearning Efficiency by Filtering Unnecessary Unlearning","created":"2025-01-28","cited_by_count":7,"area":"safety"},{"id":"2502.12430","title":"Position: Bridge the Gaps between Machine Unlearning and AI Regulation","created":"2025-02-18","cited_by_count":7,"area":"safety"},{"id":"2505.12238","title":"PANORAMA: A synthetic PII-laced dataset for studying sensitive data memorization in LLMs","created":"2025-05-18","cited_by_count":7,"area":null},{"id":"2510.08625","title":"Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models","created":"2025-10-08","cited_by_count":7,"area":"diffusion"},{"id":"2312.04542","title":"SoK: Unintended Interactions among Machine Learning Defenses and Risks","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2401.10744","title":"FinLLMs: A Framework for Financial Reasoning Dataset Generation with Large Language Models","created":"2024-01-19","cited_by_count":6,"area":"lr"},{"id":"2403.12830","title":"Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Approximate Unlearning Completeness","created":"2024-03-19","cited_by_count":6,"area":"safety"},{"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":"2506.05126","title":"Membership Inference Attacks on Sequence Models","created":"2025-06-05","cited_by_count":6,"area":"safety"},{"id":"2507.21412","title":"Cascading and Proxy Membership Inference Attacks","created":"2025-07-29","cited_by_count":6,"area":"safety"},{"id":"2509.23383","title":"Train Once, Answer All: Many Pretraining Experiments for the Cost of One","created":"2025-09-27","cited_by_count":6,"area":null},{"id":"2509.25705","title":"How Diffusion Models Memorize","created":"2025-09-30","cited_by_count":6,"area":"diffusion"},{"id":"2310.13786","title":"Fundamental Limits of Membership Inference Attacks on Machine Learning Models","created":"2023-10-20","cited_by_count":5,"area":"safety"},{"id":"2409.03741","title":"Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm?","created":"2024-09-05","cited_by_count":5,"area":"safety"},{"id":"2410.16516","title":"Scalability of memorization-based machine unlearning","created":"2024-10-21","cited_by_count":5,"area":"safety"},{"id":"2412.07192","title":"PrisonBreak: Jailbreaking Large Language Models with at Most Twenty-Five Targeted Bit-flips","created":"2024-12-10","cited_by_count":5,"area":"alignment"},{"id":"2502.10450","title":"Trustworthy AI: Safety, Bias, and Privacy -- A Survey","created":"2025-02-11","cited_by_count":5,"area":"safety"},{"id":"2504.07170","title":"Trustworthy AI Must Account for Interactions","created":"2025-04-09","cited_by_count":5,"area":null},{"id":"2504.18032","title":"Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models","created":"2025-04-25","cited_by_count":5,"area":"diffusion"},{"id":"2506.07888","title":"SoK: Data Reconstruction Attacks Against Machine Learning Models: Definition, Metrics, and Benchmark","created":"2025-06-09","cited_by_count":5,"area":null},{"id":"2406.01757","title":"Position: Cracking the Code of Cascading Disparity Towards Marginalized Communities","created":"2024-06-03","cited_by_count":4,"area":null},{"id":"2502.07830","title":"Captured by Captions: On Memorization and its Mitigation in CLIP Models","created":"2025-02-11","cited_by_count":4,"area":null},{"id":"2507.18365","title":"RecPS: Privacy Risk Scoring for Recommender Systems","created":"2025-07-24","cited_by_count":4,"area":null},{"id":"2507.19894","title":"Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocols","created":"2025-07-26","cited_by_count":4,"area":"safety"},{"id":"2508.18671","title":"Auditing Approximate Machine Unlearning for Differentially Private Models","created":"2025-08-26","cited_by_count":4,"area":"safety"},{"id":"2512.16059","title":"ContextLeak: Auditing Leakage in Private In-Context Learning Methods","created":"2025-12-18","cited_by_count":4,"area":null},{"id":"2602.16697","title":"Protecting the Undeleted in Machine Unlearning","created":"2026-02-18","cited_by_count":4,"area":"safety"},{"id":"2402.10065","title":"Some Targets Are Harder to Identify than Others: Quantifying the Target-dependent Membership Leakage","created":"2024-02-15","cited_by_count":3,"area":"safety"},{"id":"2412.21123","title":"ExpShield: Safeguarding Web Text from Unauthorized Crawling and LLM Exploitation","created":"2024-12-30","cited_by_count":3,"area":"safety"},{"id":"2501.17501","title":"How Much Do Code Language Models Remember? An Investigation on Data Extraction Attacks before and after Fine-tuning","created":"2025-01-29","cited_by_count":3,"area":"safety"},{"id":"2509.11080","title":"Membership Inference Attacks on Recommender System: A Survey","created":"2025-09-14","cited_by_count":3,"area":"safety"},{"id":"2511.05865","title":"CGCE: Classifier-Guided Concept Erasure in Generative Models","created":"2025-11-08","cited_by_count":3,"area":"safety"},{"id":"2602.03410","title":"UnHype: CLIP-Guided Hypernetworks for Dynamic LoRA Unlearning","created":"2026-02-03","cited_by_count":3,"area":"diffusion"},{"id":"2310.08015","title":"Why Train More? Effective and Efficient Membership Inference via Memorization","created":"2023-10-12","cited_by_count":2,"area":"safety"},{"id":"2404.11056","title":"LMEraser: Large Model Unlearning through Adaptive Prompt Tuning","created":"2024-04-17","cited_by_count":2,"area":"safety"},{"id":"2405.08134","title":"Many-Shot Regurgitation (MSR) Prompting","created":"2024-05-13","cited_by_count":2,"area":"safety"},{"id":"2411.01357","title":"WaKA: Data Attribution using K-Nearest Neighbors and Membership Privacy Principles","created":"2024-11-02","cited_by_count":2,"area":"safety"},{"id":"2504.08300","title":"Large Language Models Could Be Rote Learners","created":"2025-04-11","cited_by_count":2,"area":null},{"id":"2510.03263","title":"Memory Self-Regeneration: Uncovering Hidden Knowledge in Unlearned Models","created":"2025-09-26","cited_by_count":2,"area":"safety"},{"id":"2601.15394","title":"Memorization Dynamics in Knowledge Distillation for Language Models","created":"2026-01-21","cited_by_count":2,"area":"distill"},{"id":"2605.01129","title":"Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set","created":"2026-05-01","cited_by_count":2,"area":"safety"},{"id":"2311.03075","title":"SoK: Memorisation in machine learning","created":"2023-11-06","cited_by_count":1,"area":null}],"next_cursor":"100"}