Uncertainty-weighted Loss Functions for Improved Adversarial Attacks on Semantic Segmentation

Abstract

State-of-the-art deep neural networks have been shown to be extremely powerful in a variety of perceptual tasks like semantic segmentation. However, these networks are vulnerable to adversarial perturbations of the input which are imperceptible for humans but lead to incorrect predictions. Treating image segmentation as a sum of pixel-wise classifications, adversarial attacks developed for classification models were shown to be applicable to segmentation models as well. In this work, we present simple uncertainty-based weighting schemes for the loss functions of such attacks that (i) put higher weights on pixel classifications which can more easily perturbed and (ii) zero-out the pixel-wise losses corresponding to those pixels that are already confidently misclassified. The weighting schemes can be easily integrated into the loss function of a range of well-known adversarial attackers with minimal additional computational overhead, but lead to significant improved perturbation performance, as we demonstrate in our empirical analysis on several datasets and models.

References in corpus (6)

• Uncertainty and Interpretability in Convolutional Neural Networks for Semantic Segmentation of Colorectal Polyps
• The Vulnerability of Semantic Segmentation Networks to Adversarial Attacks in Autonomous Driving: Enhancing Extensive Environment Sensing
• Time-Dynamic Estimates of the Reliability of Deep Semantic Segmentation Networks
• CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks
• Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentation
• Uncertainty-based Detection of Adversarial Attacks in Semantic Segmentation

Cited by in corpus (1)

• Detecting Adversarial Attacks in Semantic Segmentation via Uncertainty Estimation: A Deep Analysis