Advancing Adversarial Training by Injecting Booster Signal

Cited 2 time in webofscience Cited 0 time in scopus
  • Hit : 100
  • Download : 0
Recent works have demonstrated that deep neural networks (DNNs) are highly vulnerable to adversarial attacks. To defend against adversarial attacks, many defense strategies have been proposed, among which adversarial training (AT) has been demonstrated to be the most effective strategy. However, it has been known that AT sometimes hurts natural accuracy. Then, many works focus on optimizing model parameters to handle the problem. Different from the previous approaches, in this article, we propose a new approach to improve the adversarial robustness using an external signal rather than model parameters. In the proposed method, a well-optimized universal external signal called a booster signal is injected into the outside of the image which does not overlap with the original content. Then, it boosts both adversarial robustness and natural accuracy. The booster signal is optimized in parallel to model parameters step by step collaboratively. Experimental results show that the booster signal can improve both the natural and robust accuracies over the recent state-of-the-art AT methods. Also, optimizing the booster signal is general and flexible enough to be adopted on any existing AT methods.
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date
2024-04
Language
English
Article Type
Article; Early Access
Citation

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, v.35, no.9, pp.12665 - 12677

ISSN
2162-237X
DOI
10.1109/TNNLS.2023.3264256
URI
http://hdl.handle.net/10203/321171
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 2 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0