AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

Mitigating Accuracy-Robustness Trade-Off via Balanced Multi-Teacher Adversarial Distillation

Shiji Zhao, Xizhe Wang, Xingxing Wei

TPAMI 2024 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training recipes · 32 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 Normalization Loss Balance to baseline multi-teacher distillation (ablation)Baseline · CIFAR-10 PGD-satW-Robust Acc: +0.87%Improved
add Normalization Loss Balance to baseline multi-teacher distillation (ablation)Baseline · CIFAR-10 PGD-tradesW-Robust Acc: +0.56%Improved
add Normalization Loss Balance to baseline multi-teacher distillation (ablation)Baseline · CIFAR-10 CWW-Robust Acc: +0.6%Improved
add Entropy-Based Balance on top of Baseline+NLB (ablation)MTARD (Baseline+NLB) · CIFAR-10 PGD-satW-Robust Acc: +0.89%Improved
add Entropy-Based Balance on top of Baseline+NLB (ablation)MTARD (Baseline+NLB) · CIFAR-10 PGD-tradesW-Robust Acc: +0.82%Improved
add Entropy-Based Balance on top of Baseline+NLB (ablation)MTARD (Baseline+NLB) · CIFAR-10 CWW-Robust Acc: +0.94%Improved
add Normalization Loss Balance to Baseline+EBB (ablation)Baseline+EBB · CIFAR-10 PGD-satW-Robust Acc: +0.33%Improved
entropy-based balance of teacher knowledge scale (ablation)B-MTARD · CIFAR-10 teacher knowledge scaleknowledge scale ResNet-56: 2.2518 -> 1.2480Improved
raise initial temperature tau from 1 to 8 (ablation)B-MTARD · CIFAR-10 PGD-satW-Robust Acc: 69.94% -> 67.81%Hurt
raise beta from 1 to 10 (ablation)B-MTARD · CIFAR-10 PGD-satW-Robust Acc: 69.94% -> 68.86%Hurt
lower beta from 1 to 0.5 (ablation)B-MTARD · CIFAR-10 PGD-satW-Robust Acc: 69.94% -> 69.38%Hurt
replace single/robust-only distillation with balanced multi-teacher (MTARD without balance) on clean accuracyARD/RSLAD · CIFAR-10clean accuracy: 83.99% -> 88.20%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