AI Paper Atlas

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

On the Vulnerability of Skip Connections to Model Inversion Attacks

Jun Hao Koh, Sy-Tuyen Ho, Ngoc-Bao Nguyen, Ngai-Man Cheung

ECCV 2024 · Adversarial robustness and security › Attacks on text and graphs · approach: Membership inference and inversion · 8 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
remove skip connections in the last stage (stage 4) during training (ablation)ResNet-101 under PPA · Facescrub PPAattack accuracy: 83.00 -> 58.68Improved
remove skip connections in the last stage (stage 4) during training (ablation)DenseNet-121 under PPA · Facescrub PPAattack accuracy: 88.11 -> 24.48Improved
remove skip connections in stage 1 or 2 instead of stage 4 (ablation)ResNet/DenseNet under PPA · Facescrub PPAattack accuracy: ResNet-34: Skip-2 drop 12.86 vs Skip-4 drop 10.17Mixed
convert RepVGG training-time architecture to inference-time (skip connections removed via reparameterization) (ablation)RepVGG-A0/B3/D2 · Facescrub PPAattack accuracy: 85.19 -> 86.13 (A0); 67.08 -> 66.44 (D2)No clear effect
apply RoLSS instead of BiDO defenseResNet-101 · Facescrub PPAattack accuracy / natural accuracy: AttAcc 67.07 -> 58.68; Acc 90.31 -> 92.40Improved
add skip-connection scaling factor (SSF) on top of RoLSS (ablation)DenseNet-169 · Facescrub PPAnatural accuracy: 72.14 -> 92.95 (AttAcc 6.77 -> 60.99)Improved
add SSF on top of RoLSS (ablation)DenseNet-161 · Facescrub PPAattack accuracy: 20.71 -> 74.27Hurt
add two-stage training scheme (TTS) on top of RoLSS (ablation)ResNet-34 · Facescrub PPAnatural accuracy: 91.38 -> 94.40 (AttAcc 71.86 -> 81.65)Improved
apply RoLSS (remove last-stage skips) to additive and concatenative architectures (ablation)ResNet-34/50/152, EfficientNet-B0, DenseNet-161/169/201 · Facescrub PPAattack accuracy: reduction of around 10% to 15% (additive), 30% to 35% (concatenative)Improved

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