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

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

Mitigating Privacy Risk via Forget Set-Free Unlearning
Apr 12, 2026Aviraj Newatia, Michael Cooper, Viet Nguyen +1Machine Unlearning Privacy-Preserving ML
University of Toronto, Vector Institute, Toronto, ON, Canada
Efficient Unlearning through Maximizing Relearning Convergence Delay
Apr 10, 2026Khoa Tran, Simon S. WooMachine Unlearning Machine Unlearning Evaluation
CSE Department, Sungkyunkwan University, South Korea · Secure Machines Lab
An Illusion of Unlearning? Assessing Machine Unlearning Through Internal Representations
Apr 9, 2026Yichen Gao, Altay Unal, Akshay Rangamani +1Machine Unlearning Machine Unlearning Evaluation
Department of Computer Science & Engineering, The Ohio State University · Department of Data Science, New Jersey Institute of Technology
$\oslash$ Source Models Leak What They Shouldn't $\nrightarrow$ : Unlearning Zero-Shot Transfer in Domain Adaptation Through Adversarial Optimization
Apr 9, 2026Arnav Devalapally, Poornima Jain, Kartik Srinivas +1Machine Unlearning Source-Free Domain Adaptation
Indian Institute of Technology, Hyderabad · University of Michigan · Carnegie Mellon University +1
Bias Redistribution in Visual Machine Unlearning: Does Forgetting One Group Harm Another?
Apr 9, 2026Yunusa Haruna, Adamu Lawan, Ibrahim Haruna Abdulhamid +4Machine Unlearning VLM Unlearning
NewraLab, Suzhou, China · Beihang University · Beijing GoerTek Alpha Lab +3
Is your algorithm unlearning or untraining?
Apr 9, 2026Eleni Triantafillou, Ahmed Imtiaz Humayun, Monica Ribero +3Machine Unlearning Machine Unlearning Evaluation
Google · Hasso Plattner Institute
How to sketch a learning algorithm
Apr 8, 2026Sam GunnMachine Unlearning
UC Berkeley
Exclusive Unlearning
Apr 7, 2026Mutsumi Sasaki, Kouta Nakayama, Yusuke Miyao +2LLM Unlearning LLM Safety
Tohoku University · NII LLMC · The University of Tokyo
Efficient machine unlearning with minimax optimality
Apr 7, 2026Jingyi Xie, Linjun Zhang, Sai LiMachine Unlearning Statistical Learning Theory
Institute of Statistics and Big Data, Renmin University of China, Beijing 100872, China · Department of Statistics, Rutgers University, Piscataway, NJ 08854, USA · Department of Statistics and Data Science, Tsinghua University, Beijing 100084, China
PECKER: A Precisely Efficient Critical Knowledge Erasure Recipe For Machine Unlearning in Diffusion Models
Apr 7, 2026Zhiyong Ma, Zhitao Deng, Huan Tang +4Machine Unlearning Diffusion Model Unlearning
Cao Tu Li(Guangzhou) Technology Co., Ltd, China · South China University of Technology, China · Guangzhou Xinhua University, China +1
Erasure or Erosion? Evaluating Compositional Degradation in Unlearned Text-To-Image Diffusion Models
Apr 6, 2026Arian Komaei Koma, Seyed Amir Kasaei, Ali Aghayari +2Diffusion Model Unlearning Machine Unlearning
Department of Computer Engineering, Sharif University of Technology
Towards Unveiling Vulnerabilities of Large Reasoning Models in Machine Unlearning
Apr 5, 2026Aobo Chen, Chenxu Zhao, Chenglin Miao +1Machine Unlearning LLM Unlearning
Iowa State University, Ames IA 50011, USA
CURE:Circuit-Aware Unlearning for LLM-based Recommendation
Apr 4, 2026Ziheng Chen, Jiali Cheng, Zezhong Fan +4Machine Unlearning LLM Unlearning
Walmart Global Tech, Sunnyvale, CA, USA · University of Massachusetts Lowell, Lowell, MA, USA · Zhejiang University, Hangzhou, China +2
Suppression Is Not Forgetting: Residual Recoverability in Visual Concept Unlearning for VLMs
Apr 3, 2026Zhangyun Tan, Zeliang Zhang, Jiani Liu +4VLM Evaluation VLM Unlearning
University of Rochester
TRU: Targeted Reverse Update for Efficient Multimodal Recommendation Unlearning
Apr 2, 2026Zhanting Zhou, KaHou Tam, Zeyu Ma +2Recommender Systems Multimodal Recommendation
University of Electronic Science and Technology of China Chengdu, China · University of Macau Macau, Macao
Why Instruction-Based Unlearning Fails in Diffusion Models?
Apr 2, 2026Zeliang Zhang, Rui Sun, Jiani Liu +2Diffusion Model Unlearning Machine Unlearning
University of Rochester · UCLA · UCSB
Machine Unlearning under Retain-Forget Entanglement
Mar 27, 2026Jingpu Cheng, Ping Liu, Qianxiao Li +1Machine Unlearning
Department of Mathematics, National University of Singapore · Department of Computer Science, University of Nevada Reno · Department of Mathematics, Institute for Functional Intelligent Materials, National University of Singapore
Designing to Forget: Deep Semi-parametric Models for Unlearning
Mar 24, 2026Amber Yijia Zheng, Yu-Shan Tai, Raymond A. YehMachine Unlearning
Department of Computer Science, Purdue University
Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models
Mar 23, 2026Hyundong Jin, Dongyoon Han, Eunwoo KimVLM Unlearning Machine Unlearning
Chung-Ang University · NAVER AI Lab
A Concept is More Than a Word: Diversified Unlearning in Text-to-Image Diffusion Models
Mar 19, 2026Duc Hao Pham, Van Duy Truong, Duy Khanh Dinh +3Diffusion Model Unlearning Concept Erasure
VNPT AI, VNPT Group Hanoi, Vietnam · Independent Researcher Australia
Attack by Unlearning: Unlearning-Induced Adversarial Attacks on Graph Neural Networks
Mar 19, 2026Jiahao Zhang, Yilong Wang, Suhang WangGraph Unlearning Adversarial Attacks
The Pennsylvania State University University Park, PA, USA
Unlearning for One-Step Generative Models via Unbalanced Optimal Transport
Mar 17, 2026Hyundo Choi, Junhyeong An, Jinseong Park +1Machine Unlearning
Sungkyunkwan University, Seoul, Republic of Korea · Korea Institute for Advanced Study, Seoul, Republic of Korea
Models Designed to Forget: Machine Unlearning via Key Deletion
Mar 16, 2026Sonia Laguna, Jorge da Silva Goncalves, Moritz Vandenhirtz +3Machine Unlearning
Department of Computer Science, ETH Zurich, Switzerland
RAZOR: Ratio-Aware Layer Editing for Targeted Unlearning in Vision Transformers and Diffusion Models
Mar 16, 2026Ravi Ranjan, Utkarsh Grover, Xiaomin Lin +1Machine Unlearning VLM Unlearning
Florida International University Miami, USA · University of South Florida Tampa, USA
Unlearning-based sliding window for continual learning under concept drift
Mar 15, 2026Michal Wozniak, Marek Klonowski, Maciej Maczynski +1Task-Free Continual Learning Concept Drift
Wroclaw University of Science and Technology Wrocław, Poland · Rochester Institute of Technology NY, USA
Relationship-Aware Safety Unlearning for Multimodal LLMs
Mar 15, 2026Vishnu Narayanan Anilkumar, Abhijith Sreesylesh Babu, Trieu Hai Vo +2MLLM Unlearning LLM Safety
Florida International University
Stake the Points: Structure-Faithful Instance Unlearning
Mar 13, 2026Kiseong Hong, JungKyoo Shin, Eunwoo KimMachine Unlearning
Chung-Ang University
The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning
Mar 11, 2026Raj Sanjay Shah, Jing Huang, Keerthiram Murugesan +2LLM Unlearning Machine Unlearning Evaluation
Georgia Institute of Technology · Stanford University · IBM Research
Reference-Guided Machine Unlearning
Mar 11, 2026Jonas Mirlach, Sonia Laguna, Julia E. VogtMachine Unlearning
Department of Computer Science, ETH Zurich
Parameter-Efficient Token Embedding Editing for Clinical Class-Level Unlearning
Mar 11, 2026Iyad Ait Hou, Shrenik Borad, Harsh Sharma +3Machine Unlearning Language Model Editing
Department of Computer Science, The George Washington University, Washington, DC · Center for Speech and Language Processing, Johns Hopkins University, Baltimore, MD

Apr 12, 2026J/K move · Enter open · S save

Mitigating Privacy Risk via Forget Set-Free Unlearning

Aviraj Newatia, Michael Cooper, Viet Nguyen, Rahul G. Krishnan

University of Toronto, Vector Institute, Toronto, ON, Canada

Machine Unlearning Privacy-Preserving ML LLM Unlearning

Open paper AskPDF arXiv

Training machine learning models requires the storage of large datasets, which often contain sensitive or private data. Storing data is associated with a number of potential risks which increase over time, such as database breaches and malicious adversaries. Machine unlearning is the study of methods to efficiently remove the influence of training data subsets from previously-trained models. Existing unlearning methods typically require direct access to the "forget set" -- the data to be forgotten-and organisations must retain this data for unlearning rather than deleting it immediately upon request, increasing risks associated with the forget set. We introduce partially-blind unlearning -- utilizing auxiliary information to unlearn without explicit access to the forget set. We also propose a practical framework Reload, a partially-blind method based on gradient optimization and structured weight sparsification to operationalize partially-blind unlearning. We show that Reload efficiently unlearns, approximating models retrained from scratch, and outperforms several forget set-dependent approaches. On language models, Reload unlearns entities using <0.025% of the retain set and <7% of model weights in <8 minutes on Llama2-7B. In the corrective case, Reload achieves unlearning even when only 10% of corrupted data is identified.