Chaojian Yu
7 papers · 2018–2025 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🏃
Academic Marathon · Sprint
🚀
Conference Pioneer
Top co-authors
Research topics
Keywords
adversarial training
(4)
catastrophic overfitting
(2)
adversarial robustness
(2)
data augmentation
(1)
deep learning
(1)
loss landscape
(1)
gradient descent
(1)
weight perturbation
(1)
saliency map
(1)
adversarial attack
(1)
deep neural network
(1)
robust overfitting
(1)
adversarial example
(1)
robust generalization
(1)
deep network
(1)
adversarial data
(1)
gradient decoupling
(1)
decision boundaries
(1)
neural network
(1)
single-step adversarial training
(1)
Papers
FastJSMA: Accelerating Jacobian-based Saliency Map Attacks through Gradient Decoupling
ICCV 2025
Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency
ICML 2024
On the Over-Memorization During Natural, Robust and Catastrophic Overfitting
ICLR 2024
Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization
NeurIPS 2023
Robust Weight Perturbation for Adversarial Training
IJCAI 2022
Understanding Robust Overfitting of Adversarial Training and Beyond
ICML 2022
Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition
ECCV 2018