Smartphone Camera Identification from Low-Mid Frequency DCT Coefficients of Dark Images

Abstract

Camera sensor identification can have numerous forensics and authentication applications. In this work, we follow an identification methodology for smartphone camera sensors using properties of the Dark Signal Nonuniformity (DSNU) in the collected images. This requires taking dark pictures, which the users can easily do by keeping the phone against their palm, and has already been proposed by various works. From such pictures, we extract low and mid frequency AC coefficients from the DCT (Discrete Cosine Transform) and classify the data with the help of machine learning techniques. Traditional algorithms such as KNN (K-Nearest Neighbor) give reasonable results in the classification, but we obtain the best results with a wide neural network, which, despite its simplicity, surpassed even a more complex network architecture that we tried. Our analysis showed that the blue channel provided the best separation, which is in contrast to previous works that have recommended the green channel for its higher encoding power.

Neural noiseprint transfer: a generic noiseprint-based counter forensics framework

“…Thus the strength of the proposed framework does not lie only in the successful attack of the noiseprint-based forensics, but it opens the door for other extensions for constrained image generation problems. For example, the proposed framework in this study may be adapted for attacking other noise-based forensic methods that are built on patterns such as the PRNU ( Chen et al, 2008 ) and the Dark Signal Nonuniformity (DSNU) ( Berdich & Groza, 2022 ). The framework could produce newly synthesized images with similar contents to forged images under the constraints of satisfying authentic patterns.…”