Noisesniffer: a Fully Automatic Image Forgery Detector Based on Noise Analysis

Marina Gardella (1) , Pablo Musé (2) , Jean-Michel Morel (1) , Miguel Colom (1, 3)

1 CB - CB - Centre Borelli - UMR 9010
2 Facultad de Ingeniería
3 CMLA - Centre de Mathématiques et de Leurs Applications

Images undergo a complex processing chain from the moment light reaches the camera's sensor until the final digital image is delivered. Each of these operations leave traces on the noise model which enable forgery detection through noise analysis. In this article we define a background stochastic model which makes it possible to detect local noise anomalies characterized by their number of false alarms. The proposed method is both automatic and blind, allowing quantitative and subjectivity-free detections. Results show that the proposed method outperforms the state of the art.

Mots clés: image forensics; automatic forgery detection; noise residual; blind algorithm

Domaines: Statistiques [math.ST]; Traitement du signal et de l'image [eess.SP]

Marina Gardella, Pablo Musé, Jean-Michel Morel, Miguel Colom. Noisesniffer: a Fully Automatic Image Forgery Detector Based on Noise Analysis. 2021 IEEE International Workshop on Biometrics and Forensics (IWBF), May 2021, Rome, Italy. pp.1-6, ⟨10.1109/IWBF50991.2021.9465095⟩. ⟨hal-03243928⟩