1 citations · 2 across the 10 of their papers we have counts for
11 papers
Adversarially Trained Linear Transformers Are Optimal Robust In-Context Learners for Gaussian Mixtures
Soichiro Kumano
Adversarial training is one of the most reliable defenses against adversarial attacks, but its high computational cost must generally be paid anew for each task. Robust foundation…
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…
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…
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…
Language-guided Detection and Mitigation of Unknown Dataset Bias
Zaiying Zhao, Soichiro Kumano, Toshihiko Yamasaki
Dataset bias is a significant problem in training fair classifiers. When attributes unrelated to classification exhibit strong biases towards certain classes, classifiers trained o…
Theoretical Understanding of Learning from Adversarial Perturbations
Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki
It is not fully understood why adversarial examples can deceive neural networks and transfer between different networks. To elucidate this, several studies have hypothesized that a…
Data-Driven Prediction of Seismic Intensity Distributions Featuring Hybrid Classification-Regression Models
Koyu Mizutani, Haruki Mitarai, Kakeru Miyazaki +2
Earthquakes are among the most immediate and deadly natural disasters that humans face. Accurately forecasting the extent of earthquake damage and assessing potential risks can be…
Improving Robustness to Out-of-Distribution Data by Frequency-based Augmentation
Koki Mukai, Soichiro Kumano, Toshihiko Yamasaki
Although Convolutional Neural Networks (CNNs) have high accuracy in image recognition, they are vulnerable to adversarial examples and out-of-distribution data, and the difference…
Prediction of Seismic Intensity Distributions Using Neural Networks
Koyu Mizutani, Haruki Mitarai, Kakeru Miyazaki +3
The ground motion prediction equation is commonly used to predict the seismic intensity distribution. However, it is not easy to apply this method to seismic distributions affected…
Superclass Adversarial Attack
Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki
Adversarial attacks have only focused on changing the predictions of the classifier, but their danger greatly depends on how the class is mistaken. For example, when an automatic d…
Are DNNs fooled by extremely unrecognizable images?
Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki
Fooling images are a potential threat to deep neural networks (DNNs). These images are not recognizable to humans as natural objects, such as dogs and cats, but are misclassified b…