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

IDA: Hybrid Attestation with Support for Interrupts and TOCTOU

Fatemeh Arkannezhad (UCLA), Justin Feng (UCLA), Nader Sehatbakhsh (UCLA)

Read More

AVMON: Securing Autonomous Vehicles by Learning Control Invariants and...

Ahmed Abdo, Sakib Md Bin Malek, Xuanpeng Zhao, Nael Abu-Ghazaleh (University of California, Riverside)

Read More

EyeSeeIdentity: Exploring Natural Gaze Behaviour for Implicit User Identification...

L Yasmeen Abdrabou (Lancaster University), Mariam Hassib (Fortiss Research Institute of the Free State of Bavaria), Shuqin Hu (LMU Munich), Ken Pfeuffer (Aarhus University), Mohamed Khamis (University of Glasgow), Andreas Bulling (University of Stuttgart), Florian Alt (University of the Bundeswehr Munich)

Read More

LARMix: Latency-Aware Routing in Mix Networks

Mahdi Rahimi (KU Leuven), Piyush Kumar Sharma (KU Leuven), Claudia Diaz (KU Leuven)

Read More