The heightened emphasis on the regulation of deep generative models, propelled by escalating concerns pertaining to privacy and compliance with regulatory frameworks, underscores the imperative need for precise control mechanisms over these models. This urgency is particularly underscored by instances in which generative models generate outputs that encompass objectionable, offensive, or potentially injurious content. In response, machine unlearning has emerged to selectively forget specific knowledge or remove the influence of undesirable data subsets from pre-trained models. However, modern machine unlearning approaches typically assume access to model parameters and architectural details during unlearning, which is not always feasible. In multitude of downstream tasks, these models function as black-box systems, with inaccessible pre-trained parameters, architectures, and training data. In such scenarios, the possibility of filtering undesired outputs becomes a practical alternative. The primary goal of this study is twofold: first, to elucidate the relationship between filtering and unlearning processes, and second, to formulate a methodology aimed at mitigating the display of undesirable outputs generated from models characterized as black-box systems. Theoretical analysis in this study demonstrates that, in the context of black-box models, filtering can be seen as a form of weak unlearning. Our proposed \textbf{\textit{Feature Aware Similarity Thresholding(FAST)}} method effectively suppresses undesired outputs by systematically encoding the representation of unwanted features in the latent space.
CBD: API-Only LLM Black-Box Unlearning through Controlled Behavioral Divergence
State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications(北京邮电大学网络与交换技术国家重点实验室);Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing(北京未来区块链与隐私计算高精尖创新中心);Department of Electronic and Electrical Engineering, Sungkyunkwan University(成均馆大学电子与电气工程系)
Textual Unlearning Gives a False Sense of Unlearning
The State Key Laboratory of Blockchain and Data Security, Zhejiang University, P. R. China(区块链与数据安全国家重点实验室,浙江大学,中华人民共和国);School of Cyber Science and Technology, Zhejiang University, P. R. China(网络安全与技术学院,浙江大学,中华人民共和国);ETH Zurich, Switzerland(苏黎世联邦理工学院,瑞士)
MUC: Machine Unlearning for Contrastive Learning with Black-box Evaluation
University of Waterloo(滑铁卢大学);University of Ottawa(渥太华大学);Alibaba(阿里巴巴);CISPA Helmholtz Center for Information Security(信息安全赫尔姆霍兹中心);Vector Institute(向量研究所);Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院);University of Chinese Academy of Sciences(中国科学院大学)
GRIP: Algorithm-Agnostic Machine Unlearning for Mixture-of-Experts via Geometric Router Constraints
School of Computer Science(计算机科学学院);Georgia Institute of Technology(佐治亚理工学院);Department of Electrical Engineering(电气工程系);Tsinghua University(清华大学);School of Electrical and Computer Engineering(电气与计算机工程学院)
To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model
School of Computing;Augmented Intelligence, Arizona State University, Tempe, AZ, USA;Department of Computer Science;Engineering, Texas A\&M University, College Station, TX, USA
CURE:Circuit-Aware Unlearning for LLM-based Recommendation
University of Massachusetts Lowell(马萨诸塞大学洛厄尔分校);Zhejiang University(浙江大学);The Chinese University of Hong Kong(香港中文大学);National University of Singapore(新加坡国立大学)