Chaojian Yu
7 papers · 2018–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌉
Interdisciplinary Bridge
🌍
Conference Polyglot
(6)
🏃
Academic Marathon
(7)
🐝
Cross-Pollinator
(9)
🚀
Conference Pioneer
Conferences
ICML (2)
ECCV (1)
ICCV (1)
ICLR (1)
IJCAI (1)
NIPS (1)
Top co-authors
Keywords
adversarial training
(3)
adversarial robustness
(2)
model robustness
(1)
data augmentation
(1)
deep learning
(1)
loss landscape
(1)
gradient descent
(1)
weight perturbation
(1)
saliency map
(1)
adversarial attack
(1)
robust overfitting
(1)
adversarial example
(1)
robust generalization
(1)
deep network
(1)
adversarial datum
(1)
catastrophic overfitting
(1)
gradient decoupling
(1)
neural network
(1)
computer vision
(1)
Papers
FastJSMA: Accelerating Jacobian-based Saliency Map Attacks through Gradient Decoupling
ICCV 2025
On the Over-Memorization During Natural, Robust and Catastrophic Overfitting
ICLR 2024
Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency
ICML 2024
Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization
NIPS 2023
Understanding Robust Overfitting of Adversarial Training and Beyond
ICML 2022
Robust Weight Perturbation for Adversarial Training
IJCAI 2022
Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition
ECCV 2018