论文标题
通过超晶体嵌入来增强对抗性训练
Boosting Adversarial Training with Hypersphere Embedding
论文作者
论文摘要
对抗性训练（AT）是防止对深度学习模型的对抗性攻击的最有效防御之一。在这项工作中，我们主张将超晶体嵌入（HE）机制纳入AT程序中，通过将特征正规化到紧凑的歧管上，该特征构成了一个轻巧而有效的模块，以融合表示代表学习的力量。我们的广泛分析表明，AT和他与他的稳健性有益于几个方面的对手训练模型的鲁棒性。我们通过将其嵌入到包括PGD-AT，ALP和Trades以及Freeat和Fastat策略在内的框架中的流行框架中来验证HE的有效性和适应性。在实验中，我们在对CIFAR-10和Imagenet数据集的广泛对抗攻击下评估了我们的方法，这验证了整合他可以始终如一地增强每个在框架上的模型鲁棒性，而几乎没有额外的计算。
Adversarial training (AT) is one of the most effective defenses against adversarial attacks for deep learning models. In this work, we advocate incorporating the hypersphere embedding (HE) mechanism into the AT procedure by regularizing the features onto compact manifolds, which constitutes a lightweight yet effective module to blend in the strength of representation learning. Our extensive analyses reveal that AT and HE are well coupled to benefit the robustness of the adversarially trained models from several aspects. We validate the effectiveness and adaptability of HE by embedding it into the popular AT frameworks including PGD-AT, ALP, and TRADES, as well as the FreeAT and FastAT strategies. In the experiments, we evaluate our methods under a wide range of adversarial attacks on the CIFAR-10 and ImageNet datasets, which verifies that integrating HE can consistently enhance the model robustness for each AT framework with little extra computation.
