AI Paper Atlas

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

Exploiting Explanations for Model Inversion Attacks

Xuejun Zhao, Wencan Zhang, Xiaokui Xiao, Brian Lim

ICCV 2021 · Adversarial robustness and security › Attacks on text and graphs · approach: Membership inference and inversion · 109 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
add target model explanations (CAM) to the inversion attack input (ablation)Prediction-only inversion · iCV-MEFED emotion taskattack accuracy: up to 33xImproved
add target model explanations (CAM) to the inversion attack input (ablation)Prediction-only inversion · CelebA ID taskattack accuracy: 2.4Improved
use contrastive alternative explanations (Sigma-CAM) instead of a single CAM (ablation)XAI-aware inversion · iCV-MEFED emotionattack accuracy: up to 39xImproved
use constituent CAMs (partial-CAM) instead of a single CAM (ablation)XAI-aware inversion · iCV-MEFED emotionattack accuracy: up to 42xImproved
add reconstructed surrogate explanations (rs-CAM) for non-explainable targets (ablation)Prediction-only inversion · non-explainable target modelsattack accuracy: up to 2.15xImproved
use Flatten input method versus Prediction-only attack (ablation)XAI-aware inversion · iCV-MEFED emotionreconstruction similarity and attack accuracyImproved
add U-Net bypass connectors versus CNN and Flatten input methods (ablation)XAI-aware inversion · iCV-MEFED emotioninversion performanceImproved
combine Flatten and U-Net input methods (ablation)XAI-aware inversion · iCV-MEFED emotioninversion performanceImproved
use Flatten input method versus CNN input method (ablation)XAI-aware inversion · iCV-MEFED emotioninversion performanceHurt
use Gradient*Input explanation versus CAM (ablation)XAI-aware inversion · iCV-MEFED emotioninversion performanceImproved
use LRP or Gradient explanations versus Gradient*Input (ablation)XAI-aware inversion · iCV-MEFED emotioninversion performanceHurt
use more relevant explanations (higher IoU with face mask) (ablation)XAI-aware inversion · iCV-MEFED emotionattack performanceImproved

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