More Like this

1. Efficient Adversarial Training With Transferable Adversarial Examples

   https://doi.org/10.1109/CVPR42600.2020.00126  

   Zheng, Haizhong; Zhang, Ziqi; Gu, Juncheng; Lee, Honglak; Prakash, Atul (June 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR))

   null (Ed.)

   Adversarial training is an effective defense method to protect classification models against adversarial attacks. However, one limitation of this approach is that it can re- quire orders of magnitude additional training time due to high cost of generating strong adversarial examples dur- ing training. In this paper, we first show that there is high transferability between models from neighboring epochs in the same training process, i.e., adversarial examples from one epoch continue to be adversarial in subsequent epochs. Leveraging this property, we propose a novel method, Adversarial Training with Transferable Adversarial Examples (ATTA), that can enhance the robustness of trained models and greatly improve the training efficiency by accumulating adversarial perturbations through epochs. Compared to state-of-the-art adversarial training methods, ATTA enhances adversarial accuracy by up to 7.2% on CIFAR10 and requires 12 ∼ 14× less training time on MNIST and CIFAR10 datasets with comparable model robustness. 

   more » « less
2. Adversarial CAPTCHAs

   https://doi.org/10.1109/TCYB.2021.3071395  

   Shi, Chenghui; Xu, Xiaogang; Ji, Shouling; Bu, Kai; Chen, Jianhai; Beyah, Raheem; Wang, Ting (January 2021, IEEE Transactions on Cybernetics)

   null (Ed.)
3. Distributed Online Learning With Adversarial Participants In An Adversarial Environment

   https://doi.org/10.1109/ICASSP49357.2023.10095178  

   Dong, Xingrong; Wu, Zhaoxian; Ling, Qing; Tian, Zhi (June 2023, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP))
4. Generalization Properties of Adversarial Training for l0 Bounded Adversarial Attacks

   https://doi.org/10.1109/ITW55543.2023.10161648  

   Delgosha, Payam; Hassani, Hamed; Pedarsani, Ramtin (April 2023, 2023 IEEE Information Theory Workshop (ITW))
5. Adversarial consistency and the uniqueness of the adversarial bayes classifier

   https://doi.org/10.1017/S0956792525000038  

   Frank, Natalie S (April 2025, European Journal of Applied Mathematics)

   Abstract Minimizing an adversarial surrogate risk is a common technique for learning robust classifiers. Prior work showed that convex surrogate losses are not statistically consistent in the adversarial context – or in other words, a minimizing sequence of the adversarial surrogate risk will not necessarily minimize the adversarial classification error. We connect the consistency of adversarial surrogate losses to properties of minimizers to the adversarial classification risk, known asadversarial Bayes classifiers. Specifically, under reasonable distributional assumptions, a convex surrogate loss is statistically consistent for adversarial learning iff the adversarial Bayes classifier satisfies a certain notion of uniqueness. 

   more » « less