对抗制
计算机科学
平滑的
边距(机器学习)
深度学习
黑匣子
人工智能
可转让性
数据点
深层神经网络
点(几何)
算法
模式识别(心理学)
机器学习
计算机视觉
数学
几何学
罗伊特
作者
Fang Yan,Zhongyuan Wang,Jikang Cheng,Ruoxi Wang,Chao Liang
标识
DOI:10.1109/icme55011.2023.00212
摘要
Carefully crafted small perturbations, when added to an image, can mislead the deep neural networks to give wrong outputs. Such mischievous images are called adversarial examples. Transfer-based black-box attacks use a surrogate white-box model to generate adversarial examples which can be transferred and attack black-box models with little known information. We propose to increase the transferability of adversarial examples by smoothing the geometric surface of loss function at the adversarial example point. By looking ahead the optimization path for a few steps, we define a future geometric vicinity using the integration of neighbourhood of those predicted data points. By sampling in this area and using the summation of gradients at those sampled data points for optimization, our method avoids local fluctuation of loss function. Experiments on ImageNet validation dataset show that our method outperforms state-of-the-art attacks by a large margin.
科研通智能强力驱动
Strongly Powered by AbleSci AI