App. Res. of Comp. Accepted Paper
Vol. 41, 2024 No. 6

Joint adversarial training method based on learnable attack step size

Yang Shikang
Liu Yi
School of Computer Science & Technology, Guangdong University of Technology, Guangzhou Guangdong 510006, China
DOI: 10.19734/j.issn.1001-3695.2023.09.0431

Abstract

Adversarial training (AT) is a powerful means to defend against adversarial attacks. However, currently available methods often struggle to strike a balance between training efficiency and adversarial robustness. Some methods increase training efficiency but decrease adversarial robustness, while others do the opposite. To achieve the best trade-off, this paper proposed a joint adversarial training method based on a learnable attack step size (FGSM-LASS) . The method includes a prediction model and a target model. The prediction model predicts an attack step size for each example, witch replaces the fixed-size attack step size used in the FGSM algorithm. Subsequently, the improved FGSM algorithm feeds both the target model parameters and original examples to generate adversarial examples. Finally, the prediction model and the target model perform joint adversarial training using these adversarial examples. Compared to the five most recent methods, FGSM-LASS is six times faster than LAS-AT, which is the best performing method in terms of robustness, with only a 1% decrease in robustness. It is 3% more robust than ATAS, which is comparable in speed. Extensive experimental results fully demonstrate that FGSM-LASS outperforms current methods in the trade-off between training speed and adversarial robustness.

Foundation Support

广东省重点研发项目(2021B0101200002)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2023.09.0431
Publish at: Application Research of Computers Accepted Paper, Vol. 41, 2024 No. 6

Publish History

[2023-12-18] Accepted Paper

Cite This Article

杨时康, 柳毅. 一种基于可学习攻击步长的联合对抗训练方法 [J]. 计算机应用研究, 2024, 41 (6). (2024-04-10). https://doi.org/10.19734/j.issn.1001-3695.2023.09.0431. (Yang Shikang, Liu Yi. Joint adversarial training method based on learnable attack step size [J]. Application Research of Computers, 2024, 41 (6). (2024-04-10). https://doi.org/10.19734/j.issn.1001-3695.2023.09.0431. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)