Block Switching：一种用于深度学习安全的随机方法
Block Switching: A Stochastic Approach for Deep Learning Security
AI总结：
本文提出基于随机性的对抗攻击防御策略 Block Switching (BS)，通过用多个并行通道替换模型层块并在运行时随机分配活动通道，有效提升防御能力且减少测试准确率下降，具有攻击无关性且可与其他防御联合使用。
摘要：
近期关于对抗攻击的研究揭示了现代深度学习模型的脆弱性。也就是说，对输入进行精心设计的微小扰动，能使具有高准确率的训练网络产生任意的错误预测，同时对人类视觉系统保持不可察觉。在本文中，我们介绍了 Block Switching (BS)，一种基于随机性的对抗攻击防御策略。BS 用多个并行通道替换模型层的一个块，活动通道在运行时被随机分配，因此对对手是不可预测的。我们通过实证表明，与 stochastic activation pruning (SAP) 等其他随机防御相比，BS 会导致更分散的输入梯度分布，并具有更优的防御有效性。与其他防御相比，BS 还具有以下特征：(i) BS 导致的测试准确率下降更少；(ii) BS 是攻击无关的；(iii) BS 与其他防御兼容，可与其他防御联合使用。
英文摘要：
Recent study of adversarial attacks has revealed the vulnerability of modern deep learning models. That is, subtly crafted perturbations of the input can make a trained network with high accuracy produce arbitrary incorrect predictions, while maintain imperceptible to human vision system. In this paper, we introduce Block Switching (BS), a defense strategy against adversarial attacks based on stochasticity. BS replaces a block of model layers with multiple parallel channels, and the active channel is randomly assigned in the run time hence unpredictable to the adversary. We show empirically that BS leads to a more dispersed input gradient distribution and superior defense effectiveness compared with other stochastic defenses such as stochastic activation pruning (SAP). Compared to other defenses, BS is also characterized by the following features: (i) BS causes less test accuracy drop; (ii) BS is attack-independent and (iii) BS is compatible with other defenses and can be used jointly with others.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
