论文标题
优化单像素黑盒对抗攻击
Optimizing One-pixel Black-box Adversarial Attacks
论文作者
论文摘要
深度神经网络（DNN）的输出可以通过对DNN进行多个呼叫来改变黑匣子设置中的输入的小扰动。但是，所需的高计算和时间使现有方法无法使用。这项工作旨在改善一像素（几个像素）黑框对抗攻击，以减少在攻击下对网络的呼叫数量。单像素攻击使用非梯度优化算法在固定数量的像素的约束下找到像素级扰动，这导致网络预测给定图像的错误标签。我们通过实验结果展示了优化算法和搜索初始位置的选择如何减少功能调用并增加攻击成功，从而使攻击在现实世界中更实用。
The output of Deep Neural Networks (DNN) can be altered by a small perturbation of the input in a black box setting by making multiple calls to the DNN. However, the high computation and time required makes the existing approaches unusable. This work seeks to improve the One-pixel (few-pixel) black-box adversarial attacks to reduce the number of calls to the network under attack. The One-pixel attack uses a non-gradient optimization algorithm to find pixel-level perturbations under the constraint of a fixed number of pixels, which causes the network to predict the wrong label for a given image. We show through experimental results how the choice of the optimization algorithm and initial positions to search can reduce function calls and increase attack success significantly, making the attack more practical in real-world settings.
