CALoR: Towards Comprehensive Model Inversion Defense
Keywords: Privacy Leakage, Model Inversion, Defense
TL;DR: We provide an in-depth analysis of intrinsic vulnerabilities of model inversion attacks, and propose a novel and comprehensive defense framework CALoR, including confidence adaptation and low-rank compression.
Abstract: Model Inversion Attacks (MIAs) aim at recovering privacy-sensitive training data from the knowledge encoded in the released machine learning models. Recent advances in the MIA field have significantly enhanced the attack performance under multiple scenarios, posing serious privacy risks of Deep Neural Networks (DNNs). However, the development of defense strategies against MIAs is relatively backward to resist the latest MIAs and existing defenses fail to achieve further trade-off between model utility and model robustness. In this paper, we provide an in-depth analysis from the perspective of intrinsic vulnerabilities of MIAs, comprehensively uncovering the weaknesses inherent in the basic pipeline, which are partially investigated in the previous defenses. Building upon these new insights, we propose a robust defense mechanism, integrating ***C**onfidence **A**daptation* and ***Lo**w-**R**ank compression*(**CALoR**). Our method includes a novel robustness-enhanced classification loss specially-designed for model inversion defenses and reveals the extraordinary effectiveness of compressing the classification header. With CALoR, we can mislead the optimization objective, reduce the leaked information and impede the backpropagation of MIAs, thus mitigating the risk of privacy leakage. Extensive experimental results demonstrate that our method achieves state-of-the-art (SOTA) defense performance against MIAs and exhibits superior generalization to existing defenses across various scenarios.
Supplementary Material: zip
Primary Area: alignment, fairness, safety, privacy, and societal considerations
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 175
Loading