Source smartphone identification for digital zoomed images

Photo Response Non–Uniformity (PRNU) is one of the most effective fingerprints used to detect the source camera of an image. Image Anonymization on the other hand, is a task of fooling the source camera identification, in order to protect the user’s anonymity in sensitive situations involving whistleblowers, social activists etc. To protect the privacy of users especially over the web, image anonymization is of huge importance. Counter–Forensic attacks on source camera identification try to make an image anonymous by nullifying the detection techniques. For almost every counter–forensic source camera identification attack, anti–counter attacks are being designed and hence there is a need to either strengthen the previous counter–forensic attacks or design a new attack altogether. In this work, we propose a new counter–forensic attack to source camera identification, using the Universal Wavelet Relative Distortion function designed for steganography. The main principle behind Universal Wavelet Relative Distortion is to embed changes in an image in regions such as textures or noisy parts which are crucial to source camera identification. We show through our experiments, when a random bit–string is inserted recursively in an image, the correlation strength of the noise residual based source camera identification gets significantly weak and such methods fail to map the source camera of the image under question. In the proposed method, the visual quality of the modified image is not changed, which makes our method a strong solution to image anonymization.

A forensic investigator performing source identification on a questioned image from a crime aims to identify the unknown camera that acquired the image. On the camera sensor, minute spatial variations in intensities between pixels, called photo response non‐uniformity (PRNU), provide a unique and persistent artifact appearing in every image acquired by the digital camera. This camera fingerprint is used to produce a score between the questioned image and an unknown camera using a court‐approved camera identification algorithm. The score is compared to a fixed threshold to determine a match or no match. Error rates for the court‐approved camera‐identification PRNU algorithm were established on a very large set of image data, making no distinction between images with different brightness levels. Camera exposure settings and in‐camera processing strive to produce a visually pleasing image, but images that are too dark or too bright are not uncommon. While prior work has shown that exposure settings can impact the accuracy of the court‐approved algorithm, these settings are often unreliable in the image metadata. In this work, we apply the court‐approved PRNU algorithm to a large data set where images are assigned a brightness level as a proxy for exposure settings using a novel classification method and then analyze error rates. We find statistically significant differences between error rates for nominal images and for images labeled dark or bright. Our result suggests that in court, the error rate of the PRNU algorithm for a questioned image may be more accurately characterized when considering the image brightness.

Photo-response non-uniformity (PRNU) noise has been well established as a reliable fingerprint of imaging sensors for source camera identification and other forensic applications. In this paper, we introduce a novel denoising method for PRNU noise extraction that considerably outperforms the existing techniques. The rationale is to use as little as one adjacent pixel in spatial domain filtering to suppress the pixel-to-pixel correlation in the estimation of the (supposedly white) PRNU noise. Experimental results are presented based on an image database of ten cameras of different models and makes. These results are embodied in the receiver operating characteristic (ROC) of source camera identification.

Identifying the source camera of a digital image using the photo response non‐uniformity (PRNU) is known as camera identification. Since digital image sensors are widely used in biometrics, it is natural to perform this investigation with biometric sensors. In this study, the authors focus on a slightly different task, which consists in clustering images with the same source sensor in a data set possibly containing images from multiple unknown distinct biometric sensors. Previous work showed unclear results because of the low quality of the extracted PRNU. They adopt different PRNU enhancement techniques together with the generation of PRNU fingerprints from uncorrelated data in order to clarify the results. Thus they propose extensions of existing source sensor attribution techniques which make use of uncorrelated data from known sensors and apply them in conjunction with existing clustering techniques. All techniques are evaluated on simulated data sets containing images from multiple sensors. The effects of the different PRNU enhancement approaches on the clustering outcome are measured by considering the relation between cohesion and separation of the clusters. Finally, an assessment on whether the PRNU enhancement techniques have been able to improve the results is given.

Camera fingerprint, namely PRNU, is a multiplicative noise source contained in each image captured by a given sensor. Source camera identification derives from similarity assessment between camera fingerprint and a candidate image; it requires the extraction of image PRNU and the estimation of camera fingerprint. To this aim, a denoising procedure is commonly applied in both cases and correlation is used for assessing similarity. However, correlation measure strongly depends on the accuracy of camera fingerprint estimation and PRNU image extraction. This paper presents a method for making more robust correlation-based source camera identification. It consists of more than one estimation of camera fingerprint; then, identification consists of the quantification of the amount of concurrence between correlation measures. It is expected higher correspondence between measures whenever the candidate image has been captured by a given device (match case); while lack of correspondence is expected whenever the image does not come from the considered device (no match case). Preliminary experimental results show that the proposed joint correlation measurements contribute to improve the precision of correlation-based source camera identification methods, especially in terms of a reduced number of false positives.

Source identification is one of the most critical problems in the field of multimedia forensics. In the last decade, researchers have been studying and improving in this field. Photo Response Non-Uniformity is one of the unique noise patterns that is being used to match a media to its originating device. Utilizing the noise patterns with machine learning algorithms has been the focus of research in recent years. Therefore, a systematic review is needed to present the latest contributions in this field. This systematic review focuses on the published work from 2015 to 2021 in source identification using noise patterns in machine learning-based systems. The results of the review indicate that a benchmark should be proposed and used to fairly compare past and future methods. Moreover, a minimum number of devices used for evaluating a model should be set by the research community in order to accurately evaluate the accuracy of the model in real-life situations.

Source camera identification (SCI) is a key issue in the field of digital forensics. This paper presents a comprehensive review of the existing methods and algorithms used for this purpose. It discusses approaches based on matrix noise analysis, including methods utilizing sensor pattern noise, photo response non-uniformity, statistical methods, aberrations analysis, as well as modern techniques based on deep neural networks and machine learning. Particular attention is paid to the effectiveness and robustness of the algorithms to different types of interference and their possible application in practical cases, such as law enforcement investigations. Moreover, we also discuss the issue of camera identification using videos and provide a brief description of popular image datasets that might be used for source camera identification method benchmarking.

Source camera identification on smartphones constitutes a fundamental task in multimedia forensics, providing essential support for applications such as image copyright protection, illegal content tracking, and digital evidence verification. Numerous techniques have been developed for this task over the past decades. Among existing approaches, Photo-Response Non-Uniformity (PRNU) has been widely recognized as a reliable device-specific fingerprint and has demonstrated remarkable performance in real-world applications. Nevertheless, the rapid advancement of computational photography technologies has introduced significant challenges: modern devices often exhibit anomalous behaviors under PRNU-based analysis. For instance, images captured by different devices may exhibit unexpected correlations, while images captured by the same device can vary substantially in their PRNU patterns. Current approaches are incapable of automatically exploring the underlying causes of these anomalous behaviors. To address this limitation, we propose a simple yet effective forensic analysis framework leveraging Exchangeable Image File Format (EXIF) metadata. Specifically, we represent EXIF metadata as type-aware word embeddings to preserve contextual information across tags. This design enables visual interpretation of the model's decision-making process and provides complementary insights for identifying the anomalous behaviors observed in modern devices. Extensive experiments conducted on three public benchmark datasets demonstrate that the proposed method not only achieves state-of-the-art performance for source camera identification but also provides valuable insights into anomalous device behaviors.

Her bir kamera sensörüne has benzersiz bir gürültü bileşeni olan PRNU (Photo Response Non-Uniformity), sayısal imge ve videoların adli analizi kapsamında ihtiyaç duyulan önemli araçlardandır. PRNU’nun en yaygın uygulama alanı olan kaynak kamera tespiti, aynı marka ve model kameraların bile PRNU karakteristiğinin birbirinden farklı oluşu ve bu örüntünün çekilen her bir resim karesi üzerine bir kamera parmak izi gibi istemsiz eklenmesi esasına dayanmaktadır. Bir test dosyasından (imge ya da video) kestirimi sağlanan PRNU sensör gürültüsü ile dosyanın kaynağı olduğu düşünülen kameraya ait referans PRNU (sabit içerikli düz duvar ya da gökyüzü görüntülerinden yüksek doğrulukta elde edilen PRNU örüntüsü) arasındaki benzerliğe göre bu kameranın test videosunun kaynağı olup olamayacağı belirlenebilir. Sayısal video çerçevelerinin imgelere göre düşük kalitede kodlanması, videolardan kestirilen PRNU sensör gürültüsünün doğruluğunu, dolayısıyla da benzerlik analizini etkilemektedir. Bu bağlamda, videolarda PRNU tabanlı kaynak kamera tespitinde, referans PRNU’nun videolardansa imgelerden elde edilmesi performans etkinliği için önemli bir hamledir. Ancak, imge ve videolar aynı kaynak kamera ile çekilmiş olsalar dahi farklı en boy oranında ve/veya çözünürlükte kaydedilmektedirler. Bu sebeple, imgelerden elde edilen PRNU izinin, sorgu videosuna ait PRNU sensör gürültüsü ile aynı foto-alıcı hücrelere karşılık gelecek forma dönüştürülmesi gerekmektedir. Bu çalışmada, bu dönüşümü sağlayan ölçekleme ve kırpma parametrelerini hassas bir şekilde hesaplayabilen bir yöntem önerilmiştir.

Current prominent camera identification methods use wavelet-based filter to extract photo-response non-uniformity (PRNU) noise as camera fingerprint [1, 2]. However, these noise features in heavily textured images can not be extracted by using wavelet-based filter effectively. In this paper, we propose a new camera identification method that uses curvelet-based filter to extract noise features in heavily textured images or non-heavily textured image. Because curvelet transform allows an optimal sparse representation of objects with C2 singularities, curvelet-based filter can extract the noise features in heavily textured images more effectively than wavelet-based filter. To increase the recognition rate for heavily textured images, we differentiate heavily textured images from non-heavily textured images by using the bivariate kurtosis of an image, and Neyman-Pearson decision is used to determine different decision thresholds.

Source camera identification can verify whether two videos were shot by the same device, which is of great significance in multimedia forensics. Most existing identification methods use convolutional neural networks to learn sensor noise patterns to identify the source camera in closed forensic scenarios. While these methodologies have achieved remarkable results, they are nonetheless constrained by two primary challenges: (1) the interference of semantic information and (2) the incongruity in feature distributions across different datasets. The former will interfere with the extraction of effective features of the model. The latter will cause the model to fit the characteristic distribution of the training data and be sensitive to unseen data features. To address these challenges, we propose a novel source camera identification framework that determines whether a video was shot by the same device by obtaining similarities between source camera features. Firstly, we extract video key frames and use the integral image to optimize the smoothing blocks selection algorithm of inter-pixel variance to remove the interference of video semantic information. Secondly, we design a residual neural network fused with a constraint layer to adaptively learn video source features. Thirdly, we introduce a triplet loss metric learning strategy to optimize the network model to improve the discriminability of the model. Finally, we design a multi-dimensional feature vector similarity fusion strategy to achieve highly generalized source camera recognition. Extensive experiments show that our method achieved an AUC value of up to 0.9714 in closed-set forensic scenarios and an AUC value of 0.882 in open-set scenarios, representing an improvement of 5% compared to the best baseline method. Furthermore, our method demonstrates effectiveness in the task of deepfake detection.

The identification of image acquisition sources is an important problem in digital image forensics. This paper introduces a new feature-based method for digital camera identification. The method, which is based on an analysis of the imaging pipeline and digital camera processing operations, employs bi-coherence and wavelet coefficient features extracted from digital images. The sequential forward feature selection algorithm is used to select features, and a support vector machine is used as the classifier for source camera identification. Experiments indicate that the source camera identification method based on bi-coherence and wavelet coefficient features is both efficient and reliable.

Photo response nonuniformity noise is a component of sensor pattern noise (SPN) of digital cameras. It characterizes the imaging devices of cameras and has been widely used in source camera identification (SCI). However, the reference SPN always be contaminated by unwanted nonunique artifacts. Previous works reported that these nonunique artifacts were periodic signals shared among cameras, which undergo the same or similar in-camera processing procedures. In this letter, we first illustrate that these nonunique artifacts, in addition to periodic signals, also contain random signals caused by the imperfection of SPN extraction method. To improve the quality of SPN and the performance of SCI, then we propose a scheme to suppress these random signals by decorrelation. In our proposed method, the reference SPN is modeled as a white Gaussian noise, while the random signals introduced by SPN extraction method are correlated noises, we suppress these correlated components to purify the SPN and enhance the performance of SCI. The experimental results on “Dresden” database show that the proposed scheme achieves better receiver operating characteristic curves than the state-of-the-art methods.

In this paper, we address the problem of unbalanced training dataset for source camera identification, namely, there are fewer training examples for some camera models compared to other camera models.A new source camera identification approach is proposed to alleviate the influence of imbalanced training dataset.In the proposed approach, firstly, we treat source camera identification as a multi-class classification problem, and decompose it into binary classification problems.After decomposing, the problem of imbalanced training dataset for multiclass classification is transformed to the problem of imbalanced training dataset for binary classification.Then, we incorporate SMOTE and AdaBoost algorithms to construct SVM ensemble to address the issue of imbalanced training dataset for binary classification.A number of experiments show the proposed approach can deal with the imbalanced training dataset effectively.

In recent years, there has been a push towards adopting artificial intelligence (AI) models in digital forensics (DF), particularly deep learning (DL) models. While these models assist DF experts, their lack of transparency raises concerns about reliability. Although eXplainable Artificial Intelligence (XAI) has progressed, current methods remain limited for DF applications. Existing visual XAI techniques do not provide sufficient clarity for challenging image forensics tasks such as Source Camera Identification (SCI), nor do they offer mechanisms to assess whether a model’s decision is correct. Most methods simply highlight influential regions without enabling examiners to validate the decision itself. Rule-based explainability is a promising strategy for increasing transparency, yet deploying it on real-world Convolutional Neural Networks (CNNs) is still challenging. Prior studies remain largely experimental and often require modifying the model to extract rules, conflicting with the integrity requirements of DF workflows. To address these gaps, this paper introduces a framework to make CNN models used in the analysis stage of digital forensics explainable. The framework, by following three fundamental steps—layers trace detection, layers majority voting, and rule extraction—provides structured and transparent visual output, and rule-based textual explainability that is understandable to the user. Based on this, the first explainable Source Camera Identification (SCI) model is introduced which is a challenging DF task to make it explainable. The explainable output allows for the rejection or confirmation of the main model’s prediction based on the decisions of the layers and compliance with the principle of integrity to the DF examiner. In addition, with the identification of 27 out of 37 incorrect predictions by the base model, the precision of the model was improved from 97.33% to 99.2%.