Paper published in a book (Scientific congresses, symposiums and conference proceedings)
Adversarial Robustness in Multi-Task Learning: Promises and Illusions
Ghamizi, Salah; Cordy, Maxime; Papadakis, Mike et al.
2022In Proceedings of the thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22)
Peer reviewed
 

Files


Full Text
AAAI22_MT_aknowledgment.pdf
Publisher postprint (312.58 kB)
Download
Annexes
AAAI22_MT_Supp.pdf
(2.72 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Robustness; Deep Learning; Multi-task
Abstract :
[en] Vulnerability to adversarial attacks is a well-known weakness of Deep Neural networks. While most of the studies focus on single-task neural networks with computer vision datasets, very little research has considered complex multi-task models that are common in real applications. In this paper, we evaluate the design choices that impact the robustness of multi-task deep learning networks. We provide evidence that blindly adding auxiliary tasks, or weighing the tasks provides a false sense of robustness. Thereby, we tone down the claim made by previous research and study the different factors which may affect robustness. In particular, we show that the choice of the task to incorporate in the loss function are important factors that can be leveraged to yield more robust models.
Disciplines :
Computer science
Author, co-author :
Ghamizi, Salah ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)
Cordy, Maxime  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SerVal
Papadakis, Mike ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)
Le Traon, Yves ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SerVal
External co-authors :
no
Language :
English
Title :
Adversarial Robustness in Multi-Task Learning: Promises and Illusions
Publication date :
2022
Event name :
The Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22)
Event organizer :
AAAI
Event date :
from 22-02-2022 to 01-03-2022
Audience :
International
Main work title :
Proceedings of the thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22)
ISBN/EAN :
1-57735-876-7
Peer reviewed :
Peer reviewed
Focus Area :
Security, Reliability and Trust
FnR Project :
FNR12669767 - Testing Self-learning Systems, 2018 (01/09/2019-31/08/2022) - Yves Le Traon
Available on ORBilu :
since 27 November 2021

Statistics


Number of views
256 (18 by Unilu)
Number of downloads
98 (7 by Unilu)

Scopus citations®
 
4
Scopus citations®
without self-citations
2

Bibliography


Similar publications



Contact ORBilu