Sanitizing diffusion-generated images via fingerprint removal and adversarial perturbation for forensic evasion
學年 114
學期 1
出版（發表）日期 2025-08-15
作品名稱 Sanitizing diffusion-generated images via fingerprint removal and adversarial perturbation for forensic evasion
作品名稱（其他語言）
著者 Meng-Luen Wu；Cheng-Pin Cheng
單位
出版者
著錄名稱、卷期、頁數 IEEE Access 13
摘要 Diffusion models have rapidly advanced the realism of synthetic image generation, posing new challenges for forensic detectors. This paper proposes a two-stage forensic evasion framework designed to undermine the detectability of diffusion-generated images. In the first stage, a spectrum-aware generative adversarial network (GAN) removes frequency-domain fingerprints that are commonly exploited by forensic models. In the second stage, adversarial perturbations are applied using the Iterative Fast Gradient Sign Method (I-FGSM) to further mislead detectors while preserving visual fidelity. Experiments conducted on COCO-based datasets demonstrate that our method significantly reduces detection accuracy across multiple state-of-the-art forensic models, including UniFD, DIGBD, and SSIP. Furthermore, we show that combining fingerprint removal with adversarial perturbation achieves stronger evasion than either method alone. Ablation studies also highlight the benefits of adaptive perturbation strengths and data augmentation for enhancing cross-model evasion. This work reveals critical vulnerabilities in current forensic approaches and underscores the need for more robust detection systems against adaptive evasion
關鍵字
語言 zh_TW
ISSN
期刊性質 國外
收錄於 SCI
產學合作
通訊作者 Meng-Luen Wu
審稿制度 是
國別 TWN
公開徵稿
出版型式 ,電子版
相關連結

機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/127814 )

SDGS 和平正義與有力的制度,產業創新與基礎設施