Towards Imperceptible and Robust Adversarial Example Attacks against Neural Networks
This addresses security vulnerabilities in machine learning systems for applications like perception tasks, but it is incremental as it builds on existing adversarial attack methods.
The paper tackles the problem of adversarial example attacks on neural networks by developing a method that considers human perception and noise tolerance, resulting in more imperceptible and robust attacks.
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.