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

Source: [Adversarial Concurrent Training: Optimizing Robustness and Accuracy Trade-off of Deep Neural Networks](<https://www.sota2.com/research/paper/68fa682a1e209131cea1a6d7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:30:00.158Z

Authors: Elahe Arani, Fahad Sarfraz, Bahram Zonooz

Published: 2020-08-16T22:14:48.000Z

## Abstract

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% standard accuracy and 44.29% robustness accuracy under a 100-iteration untargeted attack, improving upon the standard adversarial training method's 65.70% standard accuracy and 42.36% robustness.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2008.07015>)

[PDF](<https://arxiv.org/pdf/2008.07015.pdf>)
