TY - GEN
T1 - Diffusion models meet image counter-forensics
AU - Tailanián, Matías
AU - Gardella, Marina
AU - Pardo, Alvaro
AU - Musé, Pablo
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024/1/3
Y1 - 2024/1/3
N2 - From its acquisition in the camera sensors to its storage, different operations are performed to generate the final image. This pipeline imprints specific traces into the image to form a natural watermark. Tampering with an image disturbs these traces; these disruptions are clues that are used by most methods to detect and locate forgeries. In this article, we assess the capabilities of diffusion models to erase the traces left by forgers and, therefore, deceive forensics methods. Such an approach has been recently introduced for adversarial purification, achieving significant performance. We show that diffusion purification methods are well suited for counter-forensics tasks. Such approaches outperform already existing counter-forensics techniques both in deceiving forensics methods and in preserving the natural look of the purified images. The source code is publicly available at https://github.com/mtailanian/diff-cf.
AB - From its acquisition in the camera sensors to its storage, different operations are performed to generate the final image. This pipeline imprints specific traces into the image to form a natural watermark. Tampering with an image disturbs these traces; these disruptions are clues that are used by most methods to detect and locate forgeries. In this article, we assess the capabilities of diffusion models to erase the traces left by forgers and, therefore, deceive forensics methods. Such an approach has been recently introduced for adversarial purification, achieving significant performance. We show that diffusion purification methods are well suited for counter-forensics tasks. Such approaches outperform already existing counter-forensics techniques both in deceiving forensics methods and in preserving the natural look of the purified images. The source code is publicly available at https://github.com/mtailanian/diff-cf.
KW - 3D
KW - adversarial attack and defense methods
KW - Adversarial learning
KW - Algorithms
KW - Algorithms
KW - etc
KW - Generative models for image
KW - video
UR - http://www.scopus.com/inward/record.url?scp=85191998552&partnerID=8YFLogxK
U2 - 10.1109/WACV57701.2024.00388
DO - 10.1109/WACV57701.2024.00388
M3 - Contribución a la conferencia
AN - SCOPUS:85191998552
T3 - Proceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024
SP - 3913
EP - 3923
BT - Proceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024
Y2 - 4 January 2024 through 8 January 2024
ER -