454 citations · 2.5k across the 90 of their papers we have counts for
17 papers · 1 filter
NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension
Xin He, Jiangchao Yao, Yuxin Wang +5
One-shot neural architecture search (NAS) substantially improves the search efficiency by training one supernet to estimate the performance of every possible child architecture (i.…
Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks
Jianan Zhou, Jianing Zhu, Jingfeng Zhang +4
Adversarial training (AT) with imperfect supervision is significant but receives limited attention. To push AT towards more practical scenarios, we explore a brand new yet challeng…
Strength-Adaptive Adversarial Training
Chaojian Yu, Dawei Zhou, Li Shen +5
Adversarial training (AT) is proved to reliably improve network's robustness against adversarial data. However, current AT with a pre-specified perturbation budget has limitations…
Is Out-of-Distribution Detection Learnable?
Zhen Fang, Yixuan Li, Jie Lu +3
Supervised learning aims to train a classifier under the assumption that training and test data are from the same distribution. To ease the above assumption, researchers have studi…
Improving Adversarial Robustness via Mutual Information Estimation
Dawei Zhou, Nannan Wang, Xinbo Gao +4
Deep neural networks (DNNs) are found to be vulnerable to adversarial noise. They are typically misled by adversarial samples to make wrong predictions. To alleviate this negative…
Bilateral Dependency Optimization: Defending Against Model-inversion Attacks
Xiong Peng, Feng Liu, Jingfen Zhang +4
Through using only a well-trained classifier, model-inversion (MI) attacks can recover the data used for training the classifier, leading to the privacy leakage of the training dat…