Neural networks are known to be vulnerable to adversarial attacks -- slight but carefully constructed perturbations of the inputs which can drastically impair the network's performance. Many defense methods have been proposed for improving robustness of deep networks by training them on adversarially perturbed inputs. However, these models often remain vulnerable to new types of attacks not seen during training, and even to slightly stronger versions of previously seen attacks. In this work, we propose a novel approach to adversarial robustness, which builds upon the insights from the domain adaptation field. Our method, called Adversarial Feature Desensitization (AFD), aims at learning features that are invariant towards adversarial perturbations of the inputs. This is achieved through a game where we learn features that are both predictive and robust (insensitive to adversarial attacks), i.e. cannot be used to discriminate between natural and adversarial data. Empirical results on several benchmarks demonstrate the effectiveness of the proposed approach against a wide range of attack types and attack strengths. Our code is available at https://github.com/BashivanLab/afd.
翻译：众所周知,神经网络容易受到对抗性攻击 -- -- 轻微但经过仔细设计的干扰,这些输入会严重损害网络的性能;已提出许多防御方法,用对抗性扰动性投入来训练深网络,以提高深网络的稳健性;然而,这些模型往往仍然易受在训练期间未见的新类型的攻击,甚至易受以前所见攻击的较强版本的攻击;在这项工作中,我们提出了一种新颖的对抗性强力方法,它以领域适应领域的洞察力为基础。我们的方法,称为反对地功能敏化(AFD),旨在学习对对抗性侵入性投入的不稳定性特征。这是通过我们学习预测性和强势特征(对对抗性攻击不敏感)的游戏实现的,即不能用来区分自然数据和对抗性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击性攻击
相关内容
微信扫码咨询专知VIP会员