Search

Constructing adversarial examples in a black-box threat model injures the original images by introducing visual distortion. In this paper, we propose a novel black-box attack approach that can directly minimize the induced distortion by learning the noise distribution of the adversarial example, assuming only loss-oracle access to the black-box network. To quantify visual distortion, the perceptual distance between the adversarial example and the original image, is introduced in our loss. We first approximate the gradient of the corresponding non-differentiable loss function by sampling noise from the learned noise distribution. Then the distribution is updated using the estimated gradient to reduce visual distortion. The learning continues until an adversarial example is found. We validate the effectiveness of our attack on ImageNet. Our attack results in much lower distortion when compared to the state-of-the-art black-box attacks and achieves 100% success rate on InceptionV3, ResNet50 and VGG16bn. Furthermore, we theoretically prove the convergence of our model. The code is publicly available at https://github.com/Alina-1997/visual-distortion-in-attack. [ABSTRACT FROM AUTHOR]

This paper explores the task of real-time identification of dynamic events leading to a layer of situational awareness that can become a reality due to increased penetration of phasor measurement units in transmission systems. Two underlying models for this task—data driven and physics based—are explored with examples. Challenges, advantages, and drawbacks of each model are discussed based on the availability of data, attributes of such data, and processing options. Potential applications of the task to improve security of power system protection and anomaly detection in the case of a cyberattack are conceptualized. Some known issues in data communications are discussed vis-a-vis the requirements imposed by the proposed task. [ABSTRACT FROM AUTHOR]