App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 10

Diffusion-gan-based face feature obfuscation for privacy protection

Wang Bin1a,1b,1c,2
Lyu Linghui1a,1b,2
Wang Chang1a,1b,2
Zhang Lei1a,1b,2
1. Jiamusi University a. School of Information & Electronic Technology, b. Heilongjiang Province Key Laboratory of Autonomous Intelligence & Information Processing, c. Science & Technology dept, Jiamusi University, Jiamusi Heilongjiang 154007, China
2. Jiamusi Key Laboratory of Satellite Navigation Technology & Equipment Engineering Technology, Jiamusi Heilongjiang 154007, China
DOI: 10.19734/j.issn.1001-3695.2025.12.0546

Abstract

A Diffusion-based Privacy-Preserving Generative Adversarial Network (DiffPriv-GAN) was proposed to address the privacy–utility trade-off and training oscillations in GAN-based face privacy protection. The method designed a conditional encoding perturbation module, analyzed identity sensitivity across deep feature dimensions using Fisher’s linear discriminant criterion, and applied sensitivity-aware directional perturbations in feature space to achieve precise obfuscation of identity features. A joint loss was constructed to constrain reconstruction fidelity, perceptual quality, and privacy strength, thereby balancing visual quality and privacy protection. A progressive three-stage training strategy was further introduced, which gradually incorporated privacy constraints to improve training stability. Experiments on the CelebA dataset showed that DiffPriv-GAN achieved superior visual quality (SSIM= 0.89, PSNR=27.74 dB, FID =18.45) . In adversarial evaluations, the proposed method maintained high privacy-protection success rates against mainstream face-recognition models (IRSE50, IR152, FaceNet) and yielded relatively low recognition confidence on commercial APIs (Face++, Aliyun) . These results validate DiffPriv-GAN’s advantage in the privacy–utility trade-off and provide theoretical support and reference for facial-feature data privacy protection.

Foundation Support

黑龙江省高等学校基本科研业务费优秀创新团队建设项目(2023-KYYWF-0639)
佳木斯大学博士专项科研基金启动项目(JMSUBZ2022-12)
黑龙江省省属本科高校优秀青年教师基础研究支持计划(YQJH2024239)
黑龙江省自然科学基金联合基金培育项目(PL2024F002)
国家外国专家重点支撑项目(D2O25O185)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.12.0546
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 10

Publish History

[2026-07-08] Accepted Paper

Cite This Article

王斌, 吕灵慧, 王畅, 等. 基于Diffusion-GAN的人脸特征混淆隐私保护方法 [J]. 计算机应用研究, 2026, 43 (10). (2026-07-30). https://doi.org/10.19734/j.issn.1001-3695.2025.12.0546. (Wang Bin, Lyu Linghui, Wang Chang, et al. Diffusion-gan-based face feature obfuscation for privacy protection [J]. Application Research of Computers, 2026, 43 (10). (2026-07-30). https://doi.org/10.19734/j.issn.1001-3695.2025.12.0546. )

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)