DeepAI AI Chat
Log In Sign Up

Adversarial Concurrent Training: Optimizing Robustness and Accuracy Trade-off of Deep Neural Networks

08/16/2020
by   Elahe Arani, et al.
19

Adversarial training has been proven to be an effective technique for improving the adversarial robustness of models. However, there seems to be an inherent trade-off between optimizing the model for accuracy and robustness. To this end, we propose Adversarial Concurrent Training (ACT), which employs adversarial training in a collaborative learning framework whereby we train a robust model in conjunction with a natural model in a minimax game. ACT encourages the two models to align their feature space by using the task-specific decision boundaries and explore the input space more broadly. Furthermore, the natural model acts as a regularizer, enforcing priors on features that the robust model should learn. Our analyses on the behavior of the models show that ACT leads to a robust model with lower model complexity, higher information compression in the learned representations, and high posterior entropy solutions indicative of convergence to a flatter minima. We demonstrate the effectiveness of the proposed approach across different datasets and network architectures. On ImageNet, ACT achieves 68.20 accuracy and 44.29 attack, improving upon the standard adversarial training method's 65.70 standard accuracy and 42.36

READ FULL TEXT

page 1

page 7

03/25/2021

THAT: Two Head Adversarial Training for Improving Robustness at Scale

Many variants of adversarial training have been proposed, with most rese...
06/05/2022

Vanilla Feature Distillation for Improving the Accuracy-Robustness Trade-Off in Adversarial Training

Adversarial training has been widely explored for mitigating attacks aga...
10/04/2018

Feature prioritization and regularization improve standard accuracy and adversarial robustness

Adversarial training has been successfully applied to build robust model...
06/04/2019

Architecture Selection via the Trade-off Between Accuracy and Robustness

We provide a general framework for characterizing the trade-off between ...
07/24/2019

Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training

We introduce a feature scattering-based adversarial training approach fo...
05/05/2022

Can collaborative learning be private, robust and scalable?

We investigate the effectiveness of combining differential privacy, mode...
02/11/2020

Adversarial Robustness for Code

We propose a novel technique which addresses the challenge of learning a...

Code Repositories

ACT

The official PyTorch code for BMVC'20 Paper "Adversarial Concurrent Training: Optimizing Robustness and Accuracy Trade-off of Deep Neural Networks"


view repo