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

TL;DR

This paper introduces uncertainty-weighted loss functions for adversarial attacks on semantic segmentation models, significantly enhancing attack effectiveness by focusing on vulnerable pixels.

Contribution

It proposes simple, uncertainty-based weighting schemes for loss functions that improve adversarial attack performance on segmentation models with minimal computational cost.

Findings

Enhanced attack success rates on multiple datasets.

Effective targeting of vulnerable pixels in segmentation models.

Minimal additional computational overhead.

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.