Hongsheng Hu (CSIRO's Data61), Shuo Wang (CSIRO's Data61), Jiamin Chang (University of New South Wales), Haonan Zhong (University of New South Wales), Ruoxi Sun (CSIRO's Data61), Shuang Hao (University of Texas at Dallas), Haojin Zhu (Shanghai Jiao Tong University), Minhui Xue (CSIRO's Data61)

The right to be forgotten requires the removal or "unlearning" of a user's data from machine learning models. However, in the context of Machine Learning as a Service (MLaaS), retraining a model from scratch to fulfill the unlearning request is impractical due to the lack of training data on the service provider's side (the server). Furthermore, approximate unlearning further embraces a complex trade-off between utility (model performance) and privacy (unlearning performance). In this paper, we try to explore the potential threats posed by unlearning services in MLaaS, specifically over-unlearning, where more information is unlearned than expected. We propose two strategies that leverage over-unlearning to measure the impact on the trade-off balancing, under black-box access settings, in which the existing machine unlearning attacks are not applicable. The effectiveness of these strategies is evaluated through extensive experiments on benchmark datasets, across various model architectures and representative unlearning approaches. Results indicate significant potential for both strategies to undermine model efficacy in unlearning scenarios. This study uncovers an underexplored gap between unlearning and contemporary MLaaS, highlighting the need for careful considerations in balancing data unlearning, model utility, and security.

View More Papers

Enhance Stealthiness and Transferability of Adversarial Attacks with Class...

Hui Xia (Ocean University of China), Rui Zhang (Ocean University of China), Zi Kang (Ocean University of China), Shuliang Jiang (Ocean University of China), Shuo Xu (Ocean University of China)

Read More

Experimental Analyses of the Physical Surveillance Risks in Client-Side...

Ashish Hooda (University of Wisconsin-Madison), Andrey Labunets (UC San Diego), Tadayoshi Kohno (University of Washington), Earlence Fernandes (UC San Diego)

Read More

Crafter: Facial Feature Crafting against Inversion-based Identity Theft on...

Shiming Wang (Shanghai Jiao Tong University), Zhe Ji (Shanghai Jiao Tong University), Liyao Xiang (Shanghai Jiao Tong University), Hao Zhang (Shanghai Jiao Tong University), Xinbing Wang (Shanghai Jiao Tong University), Chenghu Zhou (Chinese Academy of Sciences), Bo Li (Hong Kong University of Science and Technology)

Read More