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

Sharing cyber threat intelligence: Does it really help?

Beomjin Jin (Sungkyunkwan University), Eunsoo Kim (Sungkyunkwan University), Hyunwoo Lee (KENTECH), Elisa Bertino (Purdue University), Doowon Kim (University of Tennessee, Knoxville), Hyoungshick Kim (Sungkyunkwan University)

Read More

PrintListener: Uncovering the Vulnerability of Fingerprint Authentication via the...

Man Zhou (Huazhong University of Science and Technology), Shuao Su (Huazhong University of Science and Technology), Qian Wang (Wuhan University), Qi Li (Tsinghua University), Yuting Zhou (Huazhong University of Science and Technology), Xiaojing Ma (Huazhong University of Science and Technology), Zhengxiong Li (University of Colorado Denver)

Read More

Predictive Context-sensitive Fuzzing

Pietro Borrello (Sapienza University of Rome), Andrea Fioraldi (EURECOM), Daniele Cono D'Elia (Sapienza University of Rome), Davide Balzarotti (Eurecom), Leonardo Querzoni (Sapienza University of Rome), Cristiano Giuffrida (Vrije Universiteit Amsterdam)

Read More