4 papers · 1 filter
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…
Training on Plausible Counterfactuals Removes Spurious Correlations
Shpresim Sadiku, Kartikeya Chitranshi, Hiroshi Kera +1
Plausible counterfactual explanations (p-CFEs) are perturbations that minimally modify inputs to change classifier decisions while remaining plausible under the data distribution.…
Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithms
Hiroshi Kera, Nico Pelleriti, Yuki Ishihara +2
Solving systems of polynomial equations, particularly those with finitely many solutions, is a crucial challenge across many scientific fields. Traditional methods like Gröbner and…
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…