Professor Ping Xiong, Research Fellow of the Base, has published his paper titled Game-Theoretic Machine Unlearning: Mitigating Extra Privacy Leakage in IEEE Transactions on Information Forensics and Security, a prestigious academic journal.

Abstract: With the extensive use of machine learning technologies, data providers encounter increasing privacy risks. Recent legislation, such as GDPR, obligates organizations to remove requested data and its influence from a trained model. Machine unlearning is an emerging technique designed to enable machine learning models to erase users’ private information. Although several efficient machine unlearning schemes have been proposed, these methods still have limitations. First, removing the contributions of partial data may lead to model performance degradation. Second, discrepancies between the original and generated unlearned models can be exploited by attackers to obtain target sample’s information, resulting in additional privacy leakage risks. To address above challenges, we proposed a game-theoretic machine unlearning algorithm that simulates the competitive relationship between unlearning performance and privacy protection. This algorithm comprises unlearning and privacy modules. The unlearning module possesses a loss function composed of model distance and classification error, which is used to derive the optimal strategy. The privacy module aims to make it difficult for an attacker to infer membership information from the unlearned data, thereby reducing the privacy leakage risk during the unlearning process. Additionally, the experimental results on real-world datasets demonstrate that this game-theoretic unlearning algorithm’s effectiveness and its ability to generate an unlearned model with a performance similar to that of the retrained one while mitigating extra privacy leakage risks.

Keywords: Machine unlearning/ membership inference attack/ game theory

Link: https://ieeexplore.ieee.org/document/11208174

Author profile

Ping Xiong,Professor at Zhongnan University of Economics and Law. He has presided over a number of research projects funded by the National Natural Science Foundation of China and various provincial and ministerial-level research programs. He has published more than 90 academic papers, among which over 40 are indexed by SCI/EI. He holds a patent entitled Task-Oriented Facial Privacy Protection Generation Method and System. In 2014, he published the monograph Principles and Applications of Information Security, and currently teaches courses including Introduction to Information Security and Machine Learning. In 2017, he participated in the 6th National Summit on Network and Information Security Protection and delivered an academic speech. In the same year, he took part in the completion of a research project commissioned by the Wuhan Science and Technology Innovation Bureau, and also published a review paper on privacy protection in federated learning in Journal of Network and Information Security.