计算机工程与科学2025，Vol.47Issue(12)：2181-2194,14.DOI:10.3969/j.issn.1007-130X.2025.12.010
面向图像后处理的面部操纵对抗防御方法
A facial manipulation adversarial defense method for image post-processing
摘要
Abstract
Current facial manipulation technologies have advanced to the point where they can easily modify facial attributes,making it difficult for the human eye to distinguish between real and fake ima-ges.Facial image data is readily accessible and can be exploited to forge human faces,posing a constant threat to users'personal privacy and information security.Consequently,leveraging adversarial defense methods to prevent facial images from being manipulated has become an active area of current research.However,most existing methods primarily focus on the defensive effectiveness against adversarial per-turbations added to images,lacking in-depth analysis of scenarios where these adversarial perturbations are subsequently disrupted.To address this gap,this paper proposes an adversarial defense method for facial manipulation targeting image post-processing.By conducting a comprehensive and in-depth analy-sis of original images,images with adversarial perturbations,and images with disrupted adversarial per-turbations,an image adversarial defense model based on contrastive learning is constructed.A thorough comparison and evaluation of the proposed adversarial defense method were conducted,and the experi-mental results demonstrate that the proposed method exhibits effective defense capabilities against facial manipulation.关键词
面部操纵防御/图像后处理/对抗防御/对比学习Key words
facial manipulation defense/image post-processing/adversarial defense/contrastive learn-ing分类
信息技术与安全科学引用本文复制引用
XU Kun,QI Shuren,ZHANG Yushu,WEN Wenying,ZHANG Hua..面向图像后处理的面部操纵对抗防御方法[J].计算机工程与科学,2025,47(12):2181-2194,14.基金项目
信息安全国家重点实验室开放课题(2022-MS-02) （2022-MS-02）
江西省"双千计划"科技创新高端人才项目(JXSQ2023201118) （JXSQ2023201118）
江西省自然科学基金(20232ACB212004) （20232ACB212004）
