Machine Learning models face increased concerns regarding the storage of personal user data and adverse impacts of corrupted data like backdoors or systematic bias. Machine Unlearning can address these by allowing post-hoc deletion of affected training data from a learned model. Achieving this task exactly is computationally expensive; consequently, recent works have proposed inexact unlearning algorithms to solve this approximately as well as evaluation methods to test the effectiveness of these algorithms.
In this work, we first outline some necessary criteria for evaluation methods and show no existing evaluation satisfies them all. Then, we design a stronger black-box evaluation method called the Interclass Confusion (IC) test which adversarially manipulates data during training to detect the insufficiency of unlearning procedures. We also propose two analytically motivated baseline methods~(EU-k and CF-k) which outperform several popular inexact unlearning methods. Overall, we demonstrate how adversarial evaluation strategies can help in analyzing various unlearning phenomena which can guide the development of stronger unlearning algorithms.
Machine unlearning through fine-grained model parameters perturbation
College of Computer Science and Electronic Engineering, Hunan University（湖南大学计算机与电子工程学院）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；Shenzhen Research Institute, Hunan University（湖南大学深圳研究院）；Faculty of Computing, Engineering & Media, De Montfort University（德蒙福特大学计算、工程与媒体学院）
$\textbf{AGT$^{AO}$}$: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality
School of Computer Science and Technology, Xi’an Jiaotong University, China（西安交通大学计算机科学与技术学院）；MOE KLINNS Lab, Xi’an Jiaotong University, China（西安交通大学MOE KLINNS实验室）；Shaanxi Province Key Laboratory of Big Data Knowledge Engineering, China（陕西省大数据知识工程重点实验室）
Protecting the Neural Networks against FGSM Attack Using Machine Unlearning
Department of Computer Engineering, Faculty of Engineering, Saveh Branch, Islamic Azad University（伊斯兰阿扎德大学萨韦分校工程学院计算机工程系）；Faculty of Computer Science and Engineering, Shahid Beheshti University（沙希德·贝赫什提大学计算机科学与工程学院）
Machine Unlearning Meets Adversarial Robustness via Constrained Interventions on LLMs
Department of Computer Science, Université Paris-Dauphine（巴黎-索邦大学计算机科学系）；Institute of Mathematics, EPFL（苏黎世联邦理工学院数学研究所）；Computational Engineering Lab, Empa（Empa计算工程实验室）
The Measure of Deception: An Analysis of Data Forging in Machine Unlearning
Department of Mathematics, UC San Diego（加州大学圣地亚哥分校数学系）；Department of Mathematics and Halıcıoglu Data Science Institute, UC San Diego（加州大学圣地亚哥分校数学系与哈勒吉奥卢数据科学研究所）
Auditing Language Model Unlearning via Information Decomposition
Technical University of Darmstadt（达姆施塔特工业大学）；National Research Center for Applied Cybersecurity ATHENE（ATHENE国家应用网络安全研究中心）；Georgia Institute of Technology（佐治亚理工学院）
Electrical Engineering and Computer Science, University of California, Merced, CA 95343, USA（电气工程与计算机科学系，加州大学默塞德分校）；Department of Applied Mathematics, University of California, Merced, CA 95343, USA（应用数学系，加州大学默塞德分校）；Department of Innovation and Research, North Carolina State University, Raleigh, NC, USA（创新与研究系，北卡罗来纳州立大学）；Automation (MESA) Lab, Department of Mechanical Engineering, School of Engineering, University of California, Merced, CA 95343, USA（自动化（MESA）实验室，机械工程系，工程学院，加州大学默塞德分校）
Rethinking Machine Unlearning for Large Language Models
Michigan State University（密歇根州立大学）；IBM Research（IBM研究院）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；University of California, Santa Cruz（加州大学圣克鲁兹分校）；ByteDance Research（字节跳动研究院）；Stanford University（斯坦福大学）
RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Causal Unlearning in Collaborative Optimization: Exact and Approximate Influence Reversal under Adversarial Contributions
Department of Computer Engineering, SRC, Islamic Azad University Tehran, Iran（伊朗伊斯兰Azad大学塔希尔分校计算机工程系）；School of Computer Engineering, Iran University of Science and Technology Tehran, Iran（伊朗科学技术大学塔希尔分校计算机工程系）；Meta CA, USA（美国Meta公司）
Griffith University（格里菲斯大学）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）；University of Bremen（不来梅大学）；Hanoi University of Science and Technology（河内科技大学）；The University of Queensland（昆士兰大学）
Machine Unlearning for Speaker-Agnostic Detection of Gender-Based Violence Condition in Speech
University Carlos III of Madrid (UC3M)（马德里卡斯蒂利亚-拉曼恰大学）；Department of Signal Theory and Communications（信号理论与通信系）；Ludwig-Maximilian-University of Munich（慕尼黑路德维希-马克西米利安大学）；German Center for Mental Health (DZPG)（德国心理健康中心（DZPG））；Institute of Gender Studies, Universidad Carlos III de Madrid (UC3M)（性别研究学院，马德里卡斯蒂利亚-拉曼恰大学）
Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning
Institute of Data Science, National University of Singapore（数据科学研究所，新加坡国立大学）；S-Lab, Nanyang Technological University（南洋理工大学S实验室）；College of Computing and Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学）
