Get Fooled for the Right Reason: Improving Adversarial Robustness through a Teacher-guided Curriculum Learning Approach

Sarkar, A. and Sarkar, A. and Gali, S. and Balasubramanian, Vineeth N (2021) Get Fooled for the Right Reason: Improving Adversarial Robustness through a Teacher-guided Curriculum Learning Approach. In: 35th Conference on Neural Information Processing Systems, NeurIPS 2021, 6 December 2021 through 14 December 2021, Virtual, Online.

Full text not available from this repository. (Request a copy)


Current SOTA adversarially robust models are mostly based on adversarial training (AT) and differ only by some regularizers either at inner maximization or outer minimization steps. Being repetitive in nature during the inner maximization step, they take a huge time to train. We propose a non-iterative method that enforces the following ideas during training. Attribution maps are more aligned to the actual object in the image for adversarially robust models compared to naturally trained models. Also, the allowed set of pixels to perturb an image (that changes model decision) should be restricted to the object pixels only, which reduces the attack strength by limiting the attack space. Our method achieves significant performance gains with a little extra effort (10-20%) over existing AT models and outperforms all other methods in terms of adversarial as well as natural accuracy. We have performed extensive experimentation with CIFAR-10, CIFAR-100, and TinyImageNet datasets and reported results against many popular strong adversarial attacks to prove the effectiveness of our method. © 2021 Neural information processing systems foundation. All rights reserved.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Balasubramanian, Vineeth N
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: 'current; Attack spaces; Change modeling; Learning approach; Minimisation; Modeling decisions; Non-iterative method; Regularizer; Robust modeling; Teachers'
Subjects: Computer science
Divisions: Department of Computer Science & Engineering
Depositing User: . LibTrainee 2021
Date Deposited: 24 Aug 2022 11:36
Last Modified: 24 Aug 2022 11:36
Publisher URL:
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 10287 Statistics for this ePrint Item