Can I read Adversarial Attacks Against Uncertainty Quantification on EtoBox?

Adversarial Attacks Against Uncertainty Quantification by Ledda, Emanuele; Angioni, Daniele; Piras, Giorgio; Fumera, Giorgio; Biggio, Battista; Roli, Fabio is a scholarly article available to read on EtoBox.

What is Adversarial Attacks Against Uncertainty Quantification about?

Machine-learning models can be fooled by adversarial examples, i.e., carefully-crafted input perturbations that force models to output wrong predictions. While uncertainty quantification has been recently proposed to detect adversarial inputs, under the assumption that such attacks exhibit a higher prediction uncertainty than pristine data, it has been shown that adaptive attacks specifically aimed at reducing also the uncertainty estimate can easily bypass this defense mechanism. In this work, we focus on a different adversarial scenario in which the attacker is still interested in manipulating the uncertainty estimate, but regardless of the correctness of the prediction; in particular, the goal is to undermine the use of machine-learning models when their outputs are consumed by a downstream module or by a human operator. Following such direction, we: \textit{(i)} design a threat model for attacks targeting uncertainty quantification; \textit{(ii)} devise different attack strategies on conceptually different UQ techniques spanning for both classification and semantic segmentation problems; \textit{(iii)} conduct a first complete and extensive analysis to compare the differences b

Author

Ledda, Emanuele; Angioni, Daniele; Piras, Giorgio; Fumera, Giorgio; Biggio, Battista; Roli, Fabio

Published

2023

Language

EN