PRNU-based image processing is a key asset in digital multimedia forensics. It allows for reliable device identification and effective detection and localization of image forgeries, in very general conditions. However, performance impairs significantly in challenging conditions involving low quality and quantity of data. These include working on compressed and cropped images or estimating the camera PRNU pattern based on only a few images. To boost the performance of PRNU-based analyses in such conditions, we propose to leverage the image noiseprint, a recently proposed camera-model fingerprint that has proved effective for several forensic tasks. Numerical experiments on datasets widely used for source identification prove that the proposed method ensures a significant performance improvement in a wide range of challenging situations.
fingerprint compression based on sparse representation pdf download
In this work, we tackle these problems and propose a novel source identification strategy which improves the performance of PRNU-based methods when only a few, or even just one image is available for estimation, and when only small images may be processed. To this end, we rely on a recent approach for camera model identification [12] and use it to improve the PRNU-based source device identification performance. Camera model identification has received great attention in recent years, with a steady improvement of performance, thanks to the availability of huge datasets on which it is possible to train learning-based detectors, and the introduction of convolutional neural networks (CNN). The supervised setting guarantees very good performance [13, 14], especially if deep networks are used. However, such solutions are highly vulnerable to attacks [15, 16]. To gain higher robustness, unsupervised or semi-supervised methods may be used. For example, in [17], features are extracted through a CNN, while classification relies on machine learning methods. Interestingly, only the classification step needs to be re-trained when testing on camera models that are not present in the training set. Likewise, in [18], it has been shown that proper fine-tuning strategies can be applied to camera model identification, a task that shares many features with other forensic tasks. Of course, this makes the problem easier to face, given that in a realistic scenario it is not possible to include in the training phase all the possible camera models. A further step in this direction can be found in [12], where the use of a new fingerprint has been proposed, called noiseprint, related to camera model artifacts and extracted by means of a CNN trained in Siamese modality. Noiseprints can be used in PRNU-like scenarios but require much less data to reach a satisfactory performance [19].
To assess the source identification performance of the conventional PRNU-only and the proposed PRNU+noiseprint methods, we consider several challenging cases obtained by varying the size of the image crop used for testing and the number of images used for estimating the reference patterns. In addition, we consider also the case of JPEG images compressed at two quality factors, aimed at simulating a scenario in which images are downloaded from social network accounts, where compression and resizing are routinely performed. Note that the PRNU and noiseprint reference patterns are both estimated from the very same images, since no prior information is assumed to be available on the camera models.
The next four tables refer to the case of JPEG-compressed images, with QF=90 (Tables 4 and 5) and with QF=80 (Tables 6 and 7) always for both the closed-set and open-set scenarios. First of all, with reference to the closed-set scenario, let us analyze the performance of the conventional method as the image quality impairs. Only in the ideal case the accuracy remains fully satisfactory, while it decreases dramatically in all other conditions, for example, from 0.649 (uncompressed) to 0.364 (QF=80), for (d=1024, N=1). In fact, the JPEG compression filters out as noise most of the small traces on which source identification methods rely. This is also true for the noiseprint traces. However, in the same case as before, with the robust-FLD version, the proposed method keeps granting an accuracy of 0.540, with a more limited loss from the 0.752 accuracy of uncompressed images, and a large gain with respect to the conventional method. The same behavior is observed, with random fluctuations, in all other cases, and also in the open-set scenario, so we refrain from a tedious detailed analysis. However, it is worth pointing out that, in the presence of compression, the versions based on robust estimation (r-LRT and r-FLD) provide a consistent, and often significant, improvement over those relying on ML estimation.
In this paper, we proposed to use noiseprint, a camera-model image fingerprint, to support PRNU-based forensic analyses. Numerical experiments prove that the proposed approach ensures a significant performance improvement in several challenging situations easily encountered in real-world applications.
FIGURE 5. Conventional fingerprinting method synopsis: the hemicycles (areas) related to the local, global, and temporal features are located at the outer, middle, and inner parts of the figure, respectively. Inside each hemicycle, examples of state-of-the-art solutions are presented. Conventional methods are presented in gray-shadowed rectangles while NN-based methods that also include conventional modules are represented in white rectangles.
FIGURE 7. NN-based fingerprinting method synopsis: the hemicycles (areas) related to the spatial, temporal, and spatial-temporal features are located at the outer, middle, and inner parts of the figure, respectively. Inside each hemicycle, examples of state-of-the-art solutions are presented. 2ff7e9595c
Comments