Machine Unlearning

Follow this topic Ask about this topic

Machine unlearning asks how to remove a person’s data, a class, or a learned concept from a model after training, often to support privacy, safety, or changing data rights. Approaches range from exact or certified deletion methods, such as data partitioning and noisy or influence-based updates, to approximate parameter edits, representation changes, and inference-time steering; some systems are designed from the outset to make deletion easier. Researchers evaluate methods against retrained models and test forgetting, retained utility, privacy attacks, recovery, and repeated deletion across language, vision, diffusion, graph, and multimodal systems. A central tension is that suppressed outputs do not necessarily mean information is erased, while stronger removal can damage related knowledge; scalable methods with reliable guarantees and low collateral harm remain a challenge.

Latest papers

349 papers56 papers in the last four weeks, up 70% on the four weeks before. 0.3% of all new papers.

TRACE: Data-Free Text Reconstruction Attacks against Approximate Unlearning in LLMs
Oct 22, 2026Mengying Zhang, Derui Wang, Ibrahim Khalil +3Privacy Leakage in Language Models Training Data Reconstruction Attacks
RMIT University · CSIRO · The Hong Kong University of Science and Technology +1
When Forgotten Facts Return: Relearning-Aware Unlearning of Knowledge Graph Embeddings via Tangent Kernels
Oct 22, 2026Parnian Fazel, Mohammad M Maheri, Hamed HaddadiMachine Unlearning Graph Unlearning
Imperial College London · University of Oxford
C $^2$ U in RAG: Compositional Concept Unlearning in Retrieval-Augmented Generation
Oct 21, 2026Yiyang Duan, Fan Wu, Tiantong Wu +5Retrieval-Augmented Generation Machine Unlearning
Midori Lab, Nanyang Technological University · Beihang University · Institute of Science Tokyo (formerly Tokyo Institute of Technology)
Beyond the Frame: Redundancy, Not Trajectory, Carries the Privacy Leak in Video Unlearning
Oct 20, 2026Kavyansh Tyagi, Paolo RussoMachine Unlearning Semantic Segmentation
Orthogonal Boundary Unlearning for Dual-Use Concepts in Large Language Models
Oct 20, 2026Niccolò RonchettiLLM Unlearning Machine Unlearning
Neighborhood-Aware Unlearning for Generative Recommendation
Oct 19, 2026Pierre Lubitzsch, Yubao Tang, Maarten de Rijke +1Machine Unlearning Generative Recommendation
BIFOLD & TU Berlin, Germany · University of Amsterdam, The Netherlands
Enhanced Masked Diffusion Unlearning
Oct 18, 2026Tomer Garber, Tom TirerMachine Unlearning Diffusion Model Unlearning
Faculty of Engineering, Bar-Ilan University, Ramat Gan, Israel · Red Hat
CoLU: Confidence-Weighted Layerwise Unlearning for Large Language Models
Oct 15, 2026Jingkai Guo, Ziyi Zhao, Chaitali Chakrabarti +1Machine Unlearning LLM Unlearning
School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA
Lethe: Link Inference Attacks For Evaluation of Edge Unlearning Methods
Oct 15, 2026Andrea D'Angelo, Francesco Gullo, Davide Mottin +2Graph Unlearning Machine Unlearning
University of Aarhus Aarhus, Denmark · University of L’Aquila L’Aquila, Italy · Indian Institute of Technology Delhi Delhi, India +1
Behavioral Forgetting Is Not Privacy in Machine Unlearning
Oct 15, 2026Tyler Lizzo, Larry HeckMachine Unlearning LLM Unlearning
AI Virtual Assistant (AVA) Lab, Georgia Institute of Technology
FIRM: Fisher-Informed Retention Merging for Federated LLM Unlearning
Oct 15, 2026Reeyansh Shah, Maram Hasan, Subhasis Chaudhuri +1Federated Unlearning Machine Unlearning
Indian Institute of Technology Bombay
Not All Change Is Damage: Update-Matched Unlearning for Large Language Models
Oct 15, 2026Jie Li, Youming Tao, Bowei He +1Machine Unlearning LLM Unlearning
University of Massachusetts Boston · Technische Universität Berlin · Mohamed bin Zayed University of Artificial Intelligence
Are We Really Measuring Forgetting? Pitfalls in Evaluating Machine Unlearning for Multimodal LLMs
Oct 14, 2026Oscar Chew, Po-Yi Lu, Yi-Jie Cheng +4MLLM Unlearning Machine Unlearning
Texas A&M University · National Taiwan University · Columbia University
RA $^2$ : Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning
Oct 14, 2026Zinan Ling, Yang Xiao, Ruimeng Ye +2Machine Unlearning LLM Unlearning
The University of Tulsa · Michigan State University
Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents
Oct 13, 2026Bofan Xie, Chaokun Wang, Guanchen Ge +4LLM Agent Memory Memory Agent Benchmarks
Tsinghua University · Sina Weibo
Counterfactual Certification for Sequential Unlearning with Long-Run Performance Guarantees
Oct 13, 2026Hanna Benarroch, Jamal Atif, Olivier CappéMachine Unlearning
DI-ENS · CMAP
Can Agents Truly Forget? Explore Machine Unlearning for LLM Agents
Oct 13, 2026Junkai Lin, Ge Xu, Zheng Xu +2Machine Unlearning LLM Unlearning
Institute of Automation, Chinese Academy of Sciences · The Chinese University of Hong Kong · Nanyang Technological University +2
CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation
Oct 10, 2026Chenlu Ding, Jiancan Wu, Yanchen Luo +4MLLM Unlearning Machine Unlearning
University of Science and Technology of China · Hong Kong Polytechnic University
Compositional Concepts Erasing: Disentangling Object-Style via Domain Manifold Unlearning
Oct 10, 2026Yang Xiao, Kaiyuan Deng, Gen Li +4Diffusion Model Unlearning Machine Unlearning
University of Tulsa · The University of Arizona · Clemson University +1
REDaCT: Collapse-Free Unlearning in Large Reasoning Models
Oct 8, 2026Joshua Maccoby, Wendy Hui WangMachine Unlearning LLM Unlearning
Stevens Institute of Technology Hoboken, New Jersey, USA
Not Every Change Is Necessary: Recoverable Drift in Large Language Model Unlearning
Oct 8, 2026Xunlei Chen, Qinghui Gong, Jingkun Xue +3Machine Unlearning LLM Unlearning
University of Electronic Science and Technology of China · Southwest Jiaotong University
Minimax Gaussian Mechanisms for Continual Machine Unlearning
Oct 8, 2026Qi Kuang, Yin XiaMachine Unlearning
Department of Statistics and Data Science, Fudan University
Why Forget-Only Unlearning Needs Memorization
Oct 7, 2026Luka Radić, Vikrant Singhal, Amartya SanyalMachine Unlearning
Department of Computer Science, University of Copenhagen
Removing Information Content Does Not Certify Tamper Resistance in Open-Weight Models
Oct 6, 2026Domenic Rosati, Alessa Carbo, Ali Dadsetan +5Certified Robustness Machine Unlearning
Dalhousie University · Vector Institute · Johns Hopkins University +1
How Learning Governs Unlearning across the Memorization-Generalization Spectrum
Oct 6, 2026Hwiyeong Lee, Hyelim Lim, Ingyu Bang +2Memorization in Language Models Machine Unlearning
Seoul National University · Hanyang University · Chung-Ang University
Exact Unlearning via Quantized Sufficient Statistics
Oct 5, 2026Ami Tavory, Shripad Gade, Tal Sarig +2Machine Unlearning Machine Unlearning Evaluation
Meta Platforms, Inc.
Your Unlearning Gives You Away: Identifying Erased Concepts in Diffusion Models
Oct 4, 2026Kaiyuan Deng, Yuchen Li, Yang Xiao +3Diffusion Model Unlearning Concept Erasure
The University of Arizona · Peking University · The University of Tulsa +1
UnAct: Gradient-Free Unlearning via Targeted Activation Intervention
Oct 3, 2026Saeed Abdul Muizz, Aayat Rafiq, Iqra Altaf Gillani +1Machine Unlearning
Gaash Lab National Institute of Technology Srinagar Srinagar, Jammu and Kashmir, India
Modeling Deletion Requests in Machine Unlearning
Oct 3, 2026Christian Cianfarani, Aloni CohenMachine Unlearning
Data Science Institute Columbia University New York, USA · Department of Computer Science University of Chicago Chicago, USA
FADE: Frame-Aware Diffusion-Transformer-based Multi-Concept Erasure for Video Unlearning
Oct 2, 2026Yuchen Li, Kaiyuan Deng, Chaoran Feng +2Diffusion Model Unlearning Machine Unlearning
Peking University · University of Arizona

Oct 22, 2026J/K move · Enter open · S save

TRACE: Data-Free Text Reconstruction Attacks against Approximate Unlearning in LLMs

Mengying Zhang, Derui Wang, Ibrahim Khalil, Bowen Liu+2

RMIT University · CSIRO · The Hong Kong University of Science and Technology+1

Privacy Leakage in Language Models Training Data Reconstruction Attacks LLM Unlearning Machine Unlearning

Open paper AskPDF arXiv

As large language models (LLMs) face growing demands for data removal driven by regulatory compliance, copyright concerns, and privacy protection, approximate unlearning has emerged as a practical alternative to expensive full retraining. In practice, pre- and post-unlearning model snapshots are often maintained for auditing and rollback, introducing a previously overlooked side channel. This paper demonstrates that approximate unlearning in LLM can leave residual traces within model snapshots, which may be recoverable and thus enable the privacy breaches that approximate unlearning is intended to prevent. Here, we propose TRACE, a framework that reconstructs unlearned training data given access to pre- and post-unlearning model snapshots, without any data-specific prior knowledge. To achieve this, TRACE identifies a compact set of candidate tokens from embedding-level parameter differences to constrain the search space, and assembles sequences via a contrastive scoring mechanism based on the perplexity gap between the two models. A two-stage exploration-then-completion strategy enables the recovery of multiple distinct samples. Extensive experiments on various datasets, including TOFU, MUSE, and WMDP, across multiple LLMs and six representative unlearning methods, demonstrate that TRACE achieves high-fidelity reconstruction. This paper exposes significant privacy risks in current LLM approximate unlearning deployments and highlights the need for defenses against parameter-difference leakage and appropriate management of model snapshot access.