이정엽, 권태경, 박래현, 조원영,

Vol. 34, No. 5, pp. 981-991, 10월. 2024
10.13089/JKIISC.2024.34.5.981, Full Text:
Keywords: Reverse-Update Data, Adversarial attack, Adversarial Defense, Incremental Learning
Abstract

Adversarial attacks, which induce malfunctions in AI technologies, can be applied to various domains and models, easily compromising SOTA (State-of-the-Art) models. Although adversarial defense techniques have been developed to counter these attacks, their applicability is limited due to constraints. Consequently, not only is the adoption of AI technology delayed, but also advanced research is restricted. To address this issue, this paper introduces a novel concept of adversarial data by reversing the sign of the loss function update in adversarial attacks. Experiments were conducted by applying the reverse-update adversarial data to data poisoning and adversarial training environments, showing that it can reduce the model’s performance up to 72% and is most effective in enhancing robustness in 6 out of 9 environments. Ultimately, the proposed data can stimulate extensive research on adversarial attacks and defenses, further promoting the advancement of defense technology and contributing to the safe adoption of AI.

Statistics
Cite this article