AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Improving Robustness to Model Inversion Attacks via Mutual Information Regularization

Tianhao Wang, Yuheng Zhang, Ruoxi Jia

AAAI 2021 · Adversarial robustness and security › Attacks on text and graphs · approach: Membership inference and inversion · 63 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Regularize mutual information between model input and prediction instead of using DPMID versus DP · Blackbox MI attacks on IWPC, FiveThirtyEight, FaceScrub, and CIFAR10privacy-utility tradeoffImproved
Regularize mutual information between model input and prediction instead of using DPMID versus DP · Whitebox MI attacks on CelebA and FiveThirtyEightprivacy-utility tradeoffImproved
Use MID rather than DP at comparable target-model performanceFaceScrub neural network · CelebA GMI image reconstructiontest accuracy: 80.8; 81.4No clear effect
Use MID rather than DPNeural networks under Knowledge Alignment and Update-Leaks · FaceScrub and CIFAR10ECEImproved
Use MID rather than PriorityDecision tree · FiveThirtyEightprivacy-utility tradeoffMixed
Use MID rather than output-confidence rounding or uniform-noise injectionBlackbox neural-network defenses · FaceScrub and CIFAR10 MI attacksattack robustnessImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy