research
∙
12/13/2022
What do Vision Transformers Learn? A Visual Exploration
Vision transformers (ViTs) are quickly becoming the de-facto architectur...
share
research
∙
09/30/2022
Adaptive Weight Decay: On The Fly Weight Decay Tuning for Improving Robustness
We introduce adaptive weight decay, which automatically tunes the hyper-...
research
∙
01/31/2022
Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations
Existing techniques for model inversion typically rely on hard-to-tune r...
research
∙
03/02/2021
DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations
Data poisoning and backdoor attacks manipulate training data to induce s...
research
∙
11/18/2020
Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff
Data poisoning and backdoor attacks manipulate victim models by maliciou...
research
∙
10/14/2020
Towards Accurate Quantization and Pruning via Data-free Knowledge Transfer
When large scale training data is available, one can obtain compact and ...
research
∙
03/19/2020
Breaking certified defenses: Semantic adversarial examples with spoofed robustness certificates
To deflect adversarial attacks, a range of "certified" classifiers have ...
research
∙
10/25/2019
Label Smoothing and Logit Squeezing: A Replacement for Adversarial Training?
Adversarial training is one of the strongest defenses against adversaria...
research
∙
05/20/2019
Adversarially robust transfer learning
Transfer learning, in which a network is trained on one task and re-purp...
research
∙
04/29/2019