AI Paper Atlas

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

GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks

Salah GHAMIZI, Jingfeng Zhang, Maxime Cordy, Mike Papadakis, Masashi Sugiyama, YVES LE TRAON

ICML 2023 · Adversarial robustness and security › Certified and empirical robustness · approach: Augmentation and diffusion purification · 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
add Macro domain-knowledge auxiliary task with MGDA weightingadversarial training on CIFAR-10 (ResNet-50) · CIFAR-10 full datarobust accuracy: 39.09 -> 48.38Improved
add Jigsaw or Rotation auxiliary task with MGDA weightingadversarial training on CIFAR-10 · CIFAR-10 full datarobust accuracy: Jigsaw 32.95, Rotation 36.13 vs 39.09 baselineHurt
remove curvature regularization from GAT (ablation)GAT Macro on CIFAR-10 · CIFAR-10 full datarobust accuracy: 48.38 -> 44.34 robust; clean 73.70 -> 83.47Hurt
add Macro auxiliary task in limited-data trainingadversarial fine-tuning on 10% CIFAR-10 · CIFAR-10 10% datarobust accuracy: 8.37 -> 22.42Improved
add Jigsaw auxiliary task on 10% dataadversarial fine-tuning on CIFAR-10 10% · CIFAR-10 10% datarobust accuracy: 8.37 -> 32.41 (PGD-10)Improved
add Jigsaw auxiliary task on CIFAR-10 at 50% data (ablation)adversarial training on CIFAR-10 50% · CIFAR-10 50% datarobust accuracy: 33.69 -> 23.79 (CIFAR-10 table, Jigsaw)Hurt
add Rotation auxiliary task on CIFAR-10 at 50% data (ablation)adversarial training on CIFAR-10 50% · CIFAR-10 50% datarobust accuracy: 33.69 -> 16.63Hurt
add Gender auxiliary task (CheXpert)single-task AT for Atelectasis · CheXpert Atelectasisrobust AUC: 50.00 -> 83.00Improved
add Age auxiliary task (CheXpert) (ablation)single-task AT for Atelectasis · CheXpert Atelectasisrobust AUC: 50.00 -> 46.26Hurt
add Jigsaw auxiliary task (CheXpert)single-task AT for Edema · CheXpert Edemarobust AUC: 55.69 -> 70.47Improved
add Gender auxiliary task (CheXpert Edema) (ablation)single-task AT for Edema · CheXpert Edemarobust AUC: 55.69 -> 31.46Hurt
add Macro auxiliary task (CIFAR-10 at 10% under PGD-4 evaluation) (ablation)limited-data adversarial fine-tuning · CIFAR-10 10% datarobust accuracy: 11.81 -> 42.68 (PGD-4)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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