AI Paper Atlas

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

Learning to Generate Inversion-Resistant Model Explanations

Hoyong Jeong, Suyoung Lee, Sung Ju Hwang, Sooel Son

NeurIPS 2022 · Adversarial robustness and security › Attacks on text and graphs · approach: Membership inference and inversion · 1 citations (OpenAlex)

Read the paper

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
apply GNIME to CelebA-LRP explanationsExpMI attack · CelebA-LRPSSIM: .8233 -> .4960Improved
apply GNIME to CelebA-Grad explanationsExpMI attack · CelebA-GradDeePSiM: .2470 -> .1880Improved
apply Gaussian noise (RND) to CelebA-LRP explanationsExpMI attack · CelebA-LRPSSIM: .8233 -> .6370Improved
adversary trains on FaceScrub instead of CelebAGNIME defense · CelebA-LRPTCA: 0.2086 -> 0.0012Improved
apply GNIME with gamma 0.0040 (ablation)GNIME · CelebA explanation functionalityDeePSiM: 0.6340Mixed
apply GNIME to attribute prediction from reconstructionsExpMI attack · CelebA attribute classifiersF1: 0.7672 -> 0.3048Improved
use reverse sigmoid perturbation against model-extraction ExpMI-3ExpMI-3 attack · CelebASSIM: 0.4928Improved
apply GNIME noise to explanationsexplanation functionality · CelebA-LRPDeePSiM: 0.6734Mixed

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