AI Paper Atlas

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

Adversarially Pretrained Transformers may be Universally Robust In-Context Learners

Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki

ICLR 2026 · Adversarial robustness and security › Certified and empirical robustness · approach: Robustness-accuracy trade-off analysis · 2 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
adversarially pretrain the transformer instead of standard pretrainingsingle-layer linear transformer · MNISTrobust accuracy (%): 4 -> 72Improved
adversarially pretrain the transformer instead of standard pretrainingsingle-layer linear transformer · Fashion-MNISTrobust accuracy (%): 20 -> 62Improved
adversarially pretrain the transformer instead of standard pretrainingsingle-layer linear transformer · CIFAR-10robust accuracy (%): 21 -> 34Improved
adversarially pretrain the transformer instead of standard pretrainingsingle-layer linear transformer · test distribution D_terobust accuracy (%): 0 -> 95Improved
adversarially pretrain the transformer instead of standard pretrainingsingle-layer linear transformer · MNISTclean accuracy (%): 94 -> 93Hurt
adversarially pretrain the transformer instead of standard pretrainingsingle-layer linear transformer · CIFAR-10clean accuracy (%): 68 -> 64Hurt
adversarially pretrain the transformer instead of standard pretrainingsingle-layer linear transformer · Fashion-MNISTclean accuracy (%): 91 -> 89Hurt

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