research
∙
09/10/2023
DAD++: Improved Data-free Test Time Adversarial Defense
With the increasing deployment of deep neural networks in safety-critica...
share
research
∙
07/12/2023
What Happens During Finetuning of Vision Transformers: An Invariance Based Investigation
The pretrain-finetune paradigm usually improves downstream performance o...
research
∙
11/03/2022
Robust Few-shot Learning Without Using any Adversarial Samples
The high cost of acquiring and annotating samples has made the `few-shot...
research
∙
11/03/2022
Data-free Defense of Black Box Models Against Adversarial Attacks
Several companies often safeguard their trained deep models (i.e. detail...
research
∙
10/17/2022
DE-CROP: Data-efficient Certified Robustness for Pretrained Classifiers
Certified defense using randomized smoothing is a popular technique to p...
research
∙
05/05/2022
Holistic Approach to Measure Sample-level Adversarial Vulnerability and its Utility in Building Trustworthy Systems
Adversarial attack perturbs an image with an imperceptible noise, leadin...
research
∙
04/04/2022
DAD: Data-free Adversarial Defense at Test Time
Deep models are highly susceptible to adversarial attacks. Such attacks ...
research
∙
11/09/2021
MMD-ReID: A Simple but Effective Solution for Visible-Thermal Person ReID
Learning modality invariant features is central to the problem of Visibl...
research
∙
04/26/2020