paper-with-me

홈 › Papers

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

2020-08-16 · Elahe Arani, Fahad Sarfraz, Bahram Zonooz

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.

📄 PDF Abstract BibTeX arXiv:2008.07015

Code (1)

NeurAI-Lab/ACT 공식 구현 pytorch

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

Adversarial Robustness vs Model Compression, or Both?

2019-03-29 · Shaokai Ye, Kaidi Xu, Sijia Liu, Jan-Henrik Lambrechts 외

It is well known that deep neural networks (DNNs) are vulnerable to adversarial attacks, which are implemented by adding crafted perturbations onto benign examples. Min-max robust optimization based adversarial training …

Adversarial RobustnessmodelModel CompressionNetwork Pruning

Adversarial Robustness vs. Model Compression, or Both?

2019-10-01 · ICCV 2019 10 · Shaokai Ye, Kaidi Xu, Sijia Liu, Hao Cheng 외

It is well known that deep neural networks (DNNs) are vulnerable to adversarial attacks, which are implemented by adding crafted perturbations onto benign examples. Min-max robust optimization based adversarial training …

Adversarial RobustnessmodelModel Compression

A Novel XAI-Enhanced Quantum Adversarial Networks for Velocity Dispersion Modeling in MaNGA Galaxies

2025-10-28 · Sathwik Narkedimilli, N V Saran Kumar, Aswath Babu H, Manjunath K Vanahalli 외 arxiv

Current quantum machine learning approaches often face challenges balancing predictive accuracy, robustness, and interpretability. To address this, we propose a novel quantum adversarial framework that integrates a hybri…

Quantum Machine Learning

Adversarial Training and Provable Defenses: Bridging the Gap

2020-05-01 · ICLR 2020 1 · Mislav Balunovic, Martin Vechev

We present COLT, a new method to train neural networks based on a novel combination of adversarial training and provable defenses. The key idea is to model neural network training as a procedure which includes both, the …

Advancing Adversarial Training by Injecting Booster Signal

2023-06-27 · Hong Joo Lee, Youngjoon Yu, Yong Man Ro

Recent works have demonstrated that deep neural networks (DNNs) are highly vulnerable to adversarial attacks. To defend against adversarial attacks, many defense strategies have been proposed, among which adversarial tra…

Adversarial Robustness