3 papers
cs.LG2026
Adversarially Pretrained Transformers May Be Universally Robust In-Context Learners
Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki
Adversarial training is one of the most effective defenses against adversarial attacks, but it incurs a high computational cost. In this study, we present the first theoretical ana…
cs.LG2025
Adversarial Training from Mean Field Perspective
Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki
Although adversarial training is known to be effective against adversarial examples, training dynamics are not well understood. In this study, we present the first theoretical anal…
cs.LG2025
Wide Two-Layer Networks can Learn from Adversarial Perturbations
Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki
Adversarial examples have raised several open questions, such as why they can deceive classifiers and transfer between different models. A prevailing hypothesis to explain these ph…