firstbacksecondback
230 Results
|
Spotlight
|
Tue 7:55 |
Provably Adversarially Robust Nearest Prototype Classifiers Václav Voráček · Matthias Hein |
|
|
Spotlight
|
Wed 10:40 |
Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation Wenxiao Wang · Alexander Levine · Soheil Feizi |
|
|
Poster
|
Wed 15:30 |
Certified Adversarial Robustness Under the Bounded Support Set Yiwen Kou · Qinyuan Zheng · Yisen Wang |
|
|
Spotlight
|
Thu 13:30 |
Investigating Why Contrastive Learning Benefits Robustness against Label Noise Yihao Xue · Kyle Whitecross · Baharan Mirzasoleiman |
|
|
Spotlight
|
Tue 14:40 |
Combining Diverse Feature Priors Saachi Jain · Dimitris Tsipras · Aleksander Madry |
|
|
Spotlight
|
Wed 10:35 |
FOCUS: Familiar Objects in Common and Uncommon Settings Priyatham Kattakinda · Soheil Feizi |
|
|
Poster
|
Tue 15:30 |
TPC: Transformation-Specific Smoothing for Point Cloud Models Wenda Chu · Linyi Li · Bo Li |
|
|
Spotlight
|
Tue 13:25 |
CerDEQ: Certifiable Deep Equilibrium Model Mingjie Li · Yisen Wang · Zhouchen Lin |
|
|
Poster
|
Tue 15:30 |
Provably Adversarially Robust Nearest Prototype Classifiers Václav Voráček · Matthias Hein |
|
|
Poster
|
Thu 15:00 |
Investigating Why Contrastive Learning Benefits Robustness against Label Noise Yihao Xue · Kyle Whitecross · Baharan Mirzasoleiman |
|
|
Spotlight
|
Thu 11:25 |
Fairness with Adaptive Weights Junyi Chai · Xiaoqian Wang |
|
|
Spotlight
|
Wed 10:25 |
Modeling Adversarial Noise for Adversarial Training Dawei Zhou · Nannan Wang · Bo Han · Tongliang Liu |