论文标题
评论带有添加噪声的转移性和输入转换
Comment on Transferability and Input Transformation with Additive Noise
论文作者
论文摘要
对抗性攻击已经验证了神经网络脆弱性的存在。通过在一个良性示例中添加小小的扰动，对抗性攻击成功地产生了导致深度学习模型错误分类的对抗性示例。更重要的是，由特定模型产生的对抗示例也可以欺骗其他模型而无需修改。我们称这种现象为``可传递性''。在这里，我们通过数学上证明修改的优化可以产生更容易转移的对抗性示例来分析可传递性和输入转换之间的关系。
Adversarial attacks have verified the existence of the vulnerability of neural networks. By adding small perturbations to a benign example, adversarial attacks successfully generate adversarial examples that lead misclassification of deep learning models. More importantly, an adversarial example generated from a specific model can also deceive other models without modification. We call this phenomenon ``transferability". Here, we analyze the relationship between transferability and input transformation with additive noise by mathematically proving that the modified optimization can produce more transferable adversarial examples.
