App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 4

Explainability based adversarial training method for 3D object tracking

Cheng Riran1a
Wang Xupeng1b
Lei Hang1a
Xiao Dian2,3
Yang Qing2,3
1. a. School of Information and Software Engineering, b. Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China, Chengdu 611731, China
2. Sichuan-Tibet Technology Innovation Center (Chengdu) of National Railway Co, Ltd, Chengdu 611432, China
3. China Academy of Railway Sciences Co, Ltd, Beijing 100081, China
DOI: 10.19734/j.issn.1001-3695.2025.08.0298

Abstract

3D models based on deep neural networks have made significant progress on clean datasets. However, their vulnerability to adversarial examples has led to security risks in practical applications. To address this issue, a novel adversarial training method for 3D object tracking is proposed. First, we leverage the explainability method to reveal the contribution of each point in the model input to the model prediction and study the change in the decision of the model after the attack, exploring the correlation between the sensitivity of a point to attack and its importance. Then, adversarial examples corresponding to clean samples are added during the training of model to generate a robust target model. The target model is encouraged to align the contributions of corresponding points in clean samples and adversarial samples, ensuring the consistency of the model's decisions when facing adversarial examples. Furthermore, a policy model is introduced to dynamically adjust the parameters required for generating adversarial examples to ensure their effectiveness, which can further improve the robustness of the model. Extensive experiments on multiple datasets demonstrate that this approach enables existing models to achieve better performance against advanced adversarial attacks compared to other defense methods. This demonstrates that the proposed explainability-based adversarial training method provides a feasible and efficient solution for improving the robustness of 3D object tracking models.

Foundation Support

国家自然科学基金资助项目(62072076)
四川省重大科技专项资助项目(2024ZDZX0009)
2024人工智能四川省重点实验室开放基金资助项目(2024RYY04)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.08.0298
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 4

Publish History

[2025-12-16] Accepted Paper

Cite This Article

成日冉, 王旭鹏, 雷航, 等. 基于可解释性的面向三维目标跟踪模型的对抗训练方法 [J]. 计算机应用研究, 2026, 43 (4). (2025-12-19). https://doi.org/10.19734/j.issn.1001-3695.2025.08.0298. (Cheng Riran, Wang Xupeng, Lei Hang, et al. Explainability based adversarial training method for 3D object tracking [J]. Application Research of Computers, 2026, 43 (4). (2025-12-19). https://doi.org/10.19734/j.issn.1001-3695.2025.08.0298. )

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)