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

arXiv: https://arxiv.org/abs/2008.07015 · HTML: https://mlsanity.com/paper/2008.07015/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2020.

## Built on by (most cited first, 9 of 9)

- [Mutual Adversarial Training: Learning together is better than going alone](https://mlsanity.com/paper/2112.05005/) (2021)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training](https://mlsanity.com/paper/2401.14948/) (2024)
- [InBiaseD: Inductive Bias Distillation to Improve Generalization and Robustness through Shape-awareness](https://mlsanity.com/paper/2206.05846/) (2022)
- [On the uncertainty principle of neural networks](https://mlsanity.com/paper/2205.01493/) (2022)
- [Quantum-Inspired Analysis of Neural Network Vulnerabilities: The Role of Conjugate Variables in System Attacks](https://mlsanity.com/paper/2402.10983/) (2024)
- [Topology-preserving Adversarial Training for Alleviating Natural Accuracy Degradation](https://mlsanity.com/paper/2311.17607/) (2023)
- [Adversarial Attacks and Defense Methods for Power Quality Recognition](https://mlsanity.com/paper/2202.07421/) (2022)
- [Training Image Derivatives: Increased Accuracy and Universal Robustness](https://mlsanity.com/paper/2310.14045/) (2023)

## Abstract (arXiv)

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.