Adversarial Attacks on Hidden Tasks in Multi-Task Learning

TL;DR

This paper explores the vulnerability of hidden tasks in multi-task learning models to adversarial attacks, proposing a new method that degrades hidden task performance without access to their data.

Contribution

It introduces a novel attack technique exploiting shared representations to target hidden tasks in multi-task models without direct data access.

Findings

Effective degradation of hidden task accuracy

Preservation of visible task performance

Demonstrated on CelebA and DeepFashion datasets

Abstract

Deep learning models are susceptible to adversarial attacks, where slight perturbations to input data lead to misclassification. Adversarial attacks become increasingly effective with access to information about the targeted classifier. In the context of multi-task learning, where a single model learns multiple tasks simultaneously, attackers may aim to exploit vulnerabilities in specific tasks with limited information. This paper investigates the feasibility of attacking hidden tasks within multi-task classifiers, where model access regarding the hidden target task and labeled data for the hidden target task are not available, but model access regarding the non-target tasks is available. We propose a novel adversarial attack method that leverages knowledge from non-target tasks and the shared backbone network of the multi-task model to force the model to forget knowledge related to the target task. Experimental results on CelebA and DeepFashion datasets demonstrate the effectiveness of our method in degrading the accuracy of hidden tasks while preserving the performance of visible tasks, contributing to the understanding of adversarial vulnerabilities in multi-task classifiers.