中文
相关论文

相关论文: Machine Unlearning for Responsible and Adaptive AI…

200 篇论文

Document understanding models have recently demonstrated remarkable performance by leveraging extensive collections of user documents. However, since documents often contain large amounts of personal data, their usage can pose a threat to…

计算机视觉与模式识别 · 计算机科学 2024-05-01 Lei Kang , Mohamed Ali Souibgui , Fei Yang , Lluis Gomez , Ernest Valveny , Dimosthenis Karatzas

Large language models are finetuned to refuse questions about hazardous knowledge, but these protections can often be bypassed. Unlearning methods aim at completely removing hazardous capabilities from models and make them inaccessible to…

机器学习 · 计算机科学 2025-06-03 Jakub Łucki , Boyi Wei , Yangsibo Huang , Peter Henderson , Florian Tramèr , Javier Rando

Machine unlearning for large language models (LLMs) aims to remove undesired data, knowledge, and behaviors (e.g., for safety, privacy, or copyright) while preserving useful model capabilities. Despite rapid progress over the past two…

机器学习 · 计算机科学 2025-10-10 Chongyu Fan , Changsheng Wang , Yancheng Huang , Soumyadeep Pal , Sijia Liu

As a new and promising approach, existing machine unlearning (MU) works typically emphasize theoretical formulations or optimization objectives to achieve knowledge removal. However, when deployed in real-world scenarios, such solutions…

机器学习 · 计算机科学 2025-10-31 Minyi Peng , Darian Gunamardi , Ivan Tjuawinata , Kwok-Yan Lam

Machine unlearning refers to the process of mitigating the influence of specific training data on machine learning models based on removal requests from data owners. However, one important area that has been largely overlooked in the…

密码学与安全 · 计算机科学 2025-07-17 Dayong Ye , Tianqing Zhu , Congcong Zhu , Derui Wang , Kun Gao , Zewei Shi , Sheng Shen , Wanlei Zhou , Minhui Xue

Machine learning has attracted widespread attention and evolved into an enabling technology for a wide range of highly successful applications, such as intelligent computer vision, speech recognition, medical diagnosis, and more. Yet a…

密码学与安全 · 计算机科学 2023-06-07 Heng Xu , Tianqing Zhu , Lefeng Zhang , Wanlei Zhou , Philip S. Yu

Machine unlearning is the process of removing the imprint left by specific data samples during the training of a machine learning model. AI developers, including those building personalized technologies, employ machine unlearning for…

机器学习 · 计算机科学 2026-03-10 Hanyu Duan , Yi Yang , Ahmed Abbasi , Kar Yan Tam

With the rapid advancement of generative models, associated privacy concerns have attracted growing attention. To address this, researchers have begun adapting machine unlearning techniques from traditional classification models to…

机器学习 · 计算机科学 2025-07-29 Xiaohua Feng , Jiaming Zhang , Fengyuan Yu , Chengye Wang , Li Zhang , Kaixiang Li , Yuyuan Li , Chaochao Chen , Jianwei Yin

Recent advancements in Machine Unlearning (MU) have introduced solutions to selectively remove certain training samples, such as those with outdated or sensitive information, from trained models. Despite these advancements, evaluation of MU…

机器学习 · 计算机科学 2024-12-24 Jiali Cheng , Hadi Amiri

In recent years, the notion of ``the right to be forgotten" (RTBF) has become a crucial aspect of data privacy for digital trust and AI safety, requiring the provision of mechanisms that support the removal of personal data of individuals…

密码学与安全 · 计算机科学 2024-07-17 Ziyao Liu , Yu Jiang , Jiyuan Shen , Minyi Peng , Kwok-Yan Lam , Xingliang Yuan , Xiaoning Liu

The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…

机器学习 · 计算机科学 2025-11-14 James Jin Kang , Dang Bui , Thanh Pham , Huo-Chong Ling

Machine unlearning (MU) aims to remove the influence of specific data from a trained model. However, approximate unlearning methods, often formulated as a single-objective optimization (SOO) problem, face a critical trade-off between…

机器学习 · 计算机科学 2025-10-23 Youngsik Hwang , Dong-Young Lim

Machine Unlearning (MUL) is crucial for privacy protection and content regulation, yet recent studies reveal that traces of forgotten information persist in unlearned models, enabling adversaries to resurface removed knowledge. Existing…

机器学习 · 计算机科学 2025-04-22 Hao Xuan , Xingyu Li

Machine unlearning offers a promising solution to privacy and safety concerns in large language models (LLMs) by selectively removing targeted knowledge while preserving utility. However, current methods are highly sensitive to downstream…

As the right to be forgotten has been legislated worldwide, many studies attempt to design unlearning mechanisms to protect users' privacy when they want to leave machine learning service platforms. Specifically, machine unlearning is to…

密码学与安全 · 计算机科学 2026-04-21 Weiqi Wang , Zhiyi Tian , Chenhan Zhang , Shui Yu

The article explores the cultural shift from recording to deleting information in the digital age and its implications on privacy, intellectual property (IP), and Large Language Models like ChatGPT. It begins by defining a delete culture…

计算机与社会 · 计算机科学 2023-05-25 Luciano Floridi

Machine Unlearning (MU) is critical for removing private or hazardous information from deep learning models. While MU has advanced significantly in unimodal (text or vision) settings, multimodal unlearning (MMU) remains underexplored due to…

计算机视觉与模式识别 · 计算机科学 2025-08-18 Alexey Dontsov , Dmitrii Korzh , Alexey Zhavoronkin , Boris Mikheev , Denis Bobkov , Aibek Alanov , Oleg Y. Rogov , Ivan Oseledets , Elena Tutubalina

Machine unlearning (MU) has emerged as a key mechanism for ensuring data privacy and regulatory compliance by enabling models to forget specific training samples. However, recent studies have shown that the removal of data can inadvertently…

密码学与安全 · 计算机科学 2026-05-05 Jie Fu , Nima Naderloui , Da Zhong , Yuan Hong , Wendy Hui Wang

Quantum Machine Unlearning has emerged as a foundational challenge at the intersection of quantum information theory privacypreserving computation and trustworthy artificial intelligence This paper advances QMU by establishing a formal…

量子物理 · 物理学 2026-01-14 Thanveer Shaik , Xiaohui Tao , Haoran Xie