3SAT: A Simple Self-Supervised Adversarial Training Framework

作者：Fang Jiang, Haonan He, Jiyan Sun, Jiadong Fu, Zhaorui Guo, Yinlong Liu, Wei Ma · 发表于：Proceedings of the AAAI Conference on Artificial Intelligence · 年份：2025 · DOI：10.1609/aaai.v39i16.33815 · 被引用次数：2 · 研究领域：Adversarial Robustness in Machine Learning、Anomaly Detection Techniques and Applications、Advanced Neural Network Applications

The combination of self-supervised learning and adversarial training (AT) can significantly improve the adversarial robustness of self-supervised models. However, the robustness of self-supervised adversarial training (self-AT) still lags behind that of state-of-the-art (SOTA) supervised AT (sup-AT), even though the performance of current self-supervised learning models has already matched or even surpassed that of SOTA supervised learning models. This issue raises concerns about the secure application of self-supervised learning models. The inclusion of adversarial training turns self-AT into a challenging joint optimization problem, and recent studies have shown that the data augmentation methods necessary for constructing positive pairs in self-supervised learning negatively impact the robustness improvement in self-AT. Inspired by this, we propose 3SAT, a simple self-supervised adversarial training framework. 3SAT conducts adversarial training on original, unaugmented samples, reducing the difficulty of optimizing the adversarial training subproblem and fundamentally eliminating the negative impact of data augmentation on robustness improvement. Additionally, 3SAT introduces a dynamic training objective scheduling strategy to address the issue of model training collapse during the joint optimization process when using original samples directly. 3SAT is not only structurally simple and computationally efficient, reducing self-AT training time by half, but it also improves ...