Search All 2021 Events
  Search abstracts

Filter by Keyword:

43 Results

<<   <   Page 1 of 4   >   >>
Poster
Mon 1:00 Towards Robustness Against Natural Language Word Substitutions
Xinshuai Dong · Anh Tuan Luu · Rongrong Ji · Hong Liu
Spotlight
Mon 4:40 How Benign is Benign Overfitting ?
Amartya Sanyal · Puneet Dokania · Varun Kanade · Philip Torr
Oral
Mon 5:00 Geometry-aware Instance-reweighted Adversarial Training
Jingfeng Zhang · Jianing ZHU · Gang Niu · Bo Han · Masashi Sugiyama · Mohan Kankanhalli
Poster
Mon 9:00 InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective
Boxin Wang · Shuohang Wang · Yu Cheng · Zhe Gan · Ruoxi Jia · Bo Li · Jingjing Liu
Poster
Mon 17:00 Robust Reinforcement Learning on State Observations with Learned Optimal Adversary
Huan Zhang · Hongge Chen · Duane S Boning · Cho-Jui Hsieh
Poster
Mon 17:00 On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
Ren Wang · Kaidi Xu · Sijia Liu · Pin-Yu Chen · Tsui-Wei Weng · Chuang Gan · Meng Wang
Poster
Mon 17:00 Online Adversarial Purification based on Self-supervised Learning
Changhao Shi · Chester Holtz · Gal Mishne
Spotlight
Mon 20:18 Improving Adversarial Robustness via Channel-wise Activation Suppressing
Yang Bai · Yuyuan Zeng · Yong Jiang · Shu-Tao Xia · Xingjun Ma · Yisen Wang
Poster
Tue 9:00 How Benign is Benign Overfitting ?
Amartya Sanyal · Puneet Dokania · Varun Kanade · Philip Torr
Spotlight
Tue 11:30 How Does Mixup Help With Robustness and Generalization?
Linjun Zhang · Zhun Deng · Kenji Kawaguchi · Amirata Ghorbani · James Zou
Spotlight
Tue 19:25 Orthogonalizing Convolutional Layers with the Cayley Transform
Asher Trockman · Zico Kolter
Poster
Wed 1:00 Removing Undesirable Feature Contributions Using Out-of-Distribution Data
Saehyung Lee · Changhwa Park · Hyungyu Lee · Jihun Yi · Jonghyun Lee · Sungroh Yoon