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

ShapFuzz: Efficient Fuzzing via Shapley-Guided Byte Selection

Kunpeng Zhang (Shenzhen International Graduate School, Tsinghua University), Xiaogang Zhu (Swinburne University of Technology), Xi Xiao (Shenzhen International Graduate School, Tsinghua University), Minhui Xue (CSIRO's Data61), Chao Zhang (Tsinghua University), Sheng Wen (Swinburne University of Technology)

Read More

Like, Comment, Get Scammed: Characterizing Comment Scams on Media...

Xigao Li (Stony Brook University), Amir Rahmati (Stony Brook University), Nick Nikiforakis (Stony Brook University)

Read More

Detecting Voice Cloning Attacks via Timbre Watermarking

Chang Liu (University of Science and Technology of China), Jie Zhang (Nanyang Technological University), Tianwei Zhang (Nanyang Technological University), Xi Yang (University of Science and Technology of China), Weiming Zhang (University of Science and Technology of China), NengHai Yu (University of Science and Technology of China)

Read More

Strengthening Privacy in Robust Federated Learning through Secure Aggregation

Tianyue Chu, Devriş İşler (IMDEA Networks Institute & Universidad Carlos III de Madrid), Nikolaos Laoutaris (IMDEA Networks Institute)

Read More