AI Paper Atlas

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

Shedding More Light on Robust Classifiers under the lens of Energy-based Models

Mujtaba Hussain Mirza, Maria Rosaria Briglia, Senad Beadini, Iacopo Masi

ECCV 2024 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training recipes · 1 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
use KL divergence instead of CE as inner attack loss without weighting (ablation)TRADES-style adversarial training · CIFAR-100 (ResNet-18)AutoAttack robust accuracy: 23.97 -> 24.59Improved
weight entire loss with PM_adv (MAIL-TRADES style) instead of no weighting (ablation)TRADES on CIFAR-100 · CIFAR-100 (ResNet-18)AutoAttack robust accuracy: 24.29 -> 23.26Hurt
add marginal-energy weighting (WEAT) to TRADES (ablation)TRADES · CIFAR-100 (ResNet-18)AutoAttack robust accuracy: 24.29 -> 24.88Improved
use BCE instead of CE in MART outer loss (ablation)MART-weighted loss · CIFAR-100 (ResNet-18)PGD vs AutoAttack: PGD 27.32 -> 28.24; AA 23.71 -> 23.63Mixed
weight loss by energy-based scalar instead of PM weighting (WEAT on CIFAR-10)TRADES · CIFAR-10 (ResNet-18)AutoAttack robust accuracy: 49.46 -> 49.75 (WEAT_adv); WEAT_nat 49.02No clear effect
remove high-energy correctly classified samples from AT (ablation)SAT robust model · CIFAR-10robust error under PGDHurt
start SGLD from Gaussian per class instead of random noise (ablation)robust classifier SGLD sampling (l_inf) · CIFAR-10 generationFID: 357.21 -> 64.98Improved
use PCA-based SGLD init with momentum instead of Gaussian-per-class init (l_inf) (ablation)Better DM classifier · CIFAR-10 generationIS / FID: IS 7.18 -> 7.66; FID 64.98 -> 97.38Mixed
use PCA init instead of Gaussian init under l_2 threat model (ablation)Better DM classifier · CIFAR-10 generationIS / FID: IS 8.75 -> 8.97; FID 27.71 -> 30.74Mixed
adopt l_2 instead of l_inf robust classifier for generation (ablation)SGLD generation · CIFAR-10 generationFID: 97.38 -> 30.74Improved
train with SAT instead of TRADES (generative quality)robust classifier generation · CIFAR-10 generationIS: 7.19 -> 7.96Improved

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