Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networks
Refereed conference paper presented and published in conference proceedings



摘要Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to adversarial example attack, which generates malicious output by adding slight perturbations to the input. Previous adversarial example crafting methods, however, use simple metrics to evaluate the distances between the original examples and the adversarial ones, which could be easily detected by human eyes. In addition, these attacks are often not robust due to the inevitable noises and deviation in the physical world. In this work, we present a new adversarial example attack crafting method, which takes the human perceptual system into consideration and maximizes the noise tolerance of the crafted adversarial example. Experimental results demonstrate the efficacy of the proposed technique.
著者B. Luo, Y. Liu, L. Wei, Q. Xu
會議名稱The AAAI Conference on Artificial Intelligence 2018
會議地點New Orleans

上次更新時間 2018-28-12 於 16:28