Search for: All records

Abstract Machine unlearning is a cutting‐edge technology that embodies the privacy legal principle of the right to be forgotten within the realm of machine learning (ML). It aims to remove specific data or knowledge from trained models without retraining from scratch and has gained significant attention in the field of artificial intelligence in recent years. However, the development of machine unlearning research is associated with inherent vulnerabilities and threats, posing significant challenges for researchers and practitioners. In this article, we provide the first comprehensive survey of security and privacy issues associated with machine unlearning by providing a systematic classification across different levels and criteria. Specifically, we begin by investigating unlearning‐based security attacks, where adversaries exploit vulnerabilities in the unlearning process to compromise the security of machine learning (ML) models. We then conduct a thorough examination of privacy risks associated with the adoption of machine unlearning. Additionally, we explore existing countermeasures and mitigation strategies designed to protect models from malicious unlearning‐based attacks targeting both security and privacy. Further, we provide a detailed comparison between machine unlearning‐based security and privacy attacks and traditional malicious attacks. Finally, we discuss promising future research directions for security and privacy issues posed by machine unlearning, offering insights into potential solutions and advancements in this evolving field. 

Diffusion models have begun to overshadow GANs and other generative models in industrial applications due to their superior image generation performance. The complex architecture of these models furnishes an extensive array of attack features. In light of this, we aim to design membership inference attacks (MIAs) catered to diffusion models. We first conduct an exhaustive analysis of existing MIAs on diffusion models, taking into account factors such as black-box/white-box models and the selection of attack features. We found that white-box attacks are highly applicable in real-world scenarios, and the most effective attacks presently are white-box. Departing from earlier research, which employs model loss as the attack feature for white-box MIAs, we employ model gradients in our attack, leveraging the fact that these gradients provide a more profound understanding of model responses to various samples. We subject these models to rigorous testing across a range of parameters, including training steps, timestep sampling frequency, diffusion steps, and data variance. Across all experimental settings, our method consistently demonstrated near-flawless attack performance, with attack success rate approaching 100% and attack AUCROC near 1.0. We also evaluated our attack against common defense mechanisms, and observed our attacks continue to exhibit commendable performance.