Deep neural networks have achieved remarkable performance in various applications but are extremely vulnerable to adversarial perturbation. The most representative and promising methods that can enhance model robustness, such as adversarial training and its variants, substantially degrade model accuracy on benign samples, limiting practical utility. Although incorporating extra training data can alleviate the trade-off to a certain extent, it remains unsolved to achieve both robustness and accuracy under limited training data. Here, we demonstrate the feasibility of overcoming the trade-off, by developing an adversarial feature stacking (AFS) model, which combines multiple independent feature extractors with varied levels of robustness and accuracy. Theoretical analysis is further conducted, and general principles for the selection of basic feature extractors are provided. We evaluate the AFS model on CIFAR-10 and CIFAR-100 datasets with strong adaptive attack methods, significantly advancing the state-of-the-art in terms of the trade-off. The AFS model achieves a benign accuracy improvement of ~6% on CIFAR-10 and ~10% on CIFAR-100 with comparable or even stronger robustness than the state-of-the-art adversarial training methods.
翻译:深心神经网络在各种应用中取得了显著的成绩,但极易受到对抗性扰动的影响; 最有代表性和最有希望的方法可以加强模型的稳健性,例如对抗性培训及其变体,大大降低良性样品的模型准确性,限制实用性; 虽然纳入额外培训数据可以在某种程度上减轻权衡,但对于在有限的培训数据下实现稳健性和准确性,仍然没有解决; 在这里,我们通过开发一个对抗性堆叠模型(AFS),将多种独立特征提取器和各种强度和准确性结合起来,来证明克服这种权衡的可行性; 进一步进行理论分析,并提供选择基本特征提取器的一般原则; 我们用强有力的适应性攻击方法评价ACFS模型10和CIFAR-100数据集,大大推进交易方面的先进技术; ACFS模型在CIFAR-10和IFAR-100上实现了接近于或甚至更强于州立对抗性培训方法的近似精确性改进。