In this paper we present TruFor, a forensic framework that can be applied to a large variety of image manipulation methods, from classic cheapfakes to more recent manipulations based on deep learning. We rely on the extraction of both high-level and low-level traces through a transformer-based fusion architecture that combines the RGB image and a learned noise-sensitive fingerprint. The latter learns to embed the artifacts related to the camera internal and external processing by training only on real data in a self-supervised manner. Forgeries are detected as deviations from the expected regular pattern that characterizes each pristine image. Looking for anomalies makes the approach able to robustly detect a variety of local manipulations, ensuring generalization. In addition to a pixel-level localization map and a whole-image integrity score, our approach outputs a reliability map that highlights areas where localization predictions may be error-prone. This is particularly important in forensic applications in order to reduce false alarms and allow for a large scale analysis. Extensive experiments on several datasets show that our method is able to reliably detect and localize both cheapfakes and deepfakes manipulations outperforming state-of-the-art works. Code will be publicly available at https://grip-unina.github.io/TruFor/
Manipulated images are a threat to consumers worldwide, when they are used to spread disinformation. Therefore, Comprint enables forgery detection by utilizing JPEG-compression fingerprints. This paper evaluates the impact of the training set on Comprint's performance. Most interestingly, we found that including images compressed with low quality factors during training does not have a significant effect on the accuracy, whereas incorporating recompression boosts the robustness. As such, consumers can use Comprint on their smartphones to verify the authenticity of images.
Over the past decade, there has been tremendous progress in creating synthetic media, mainly thanks to the development of powerful methods based on generative adversarial networks (GAN). Very recently, methods based on diffusion models (DM) have been gaining the spotlight. In addition to providing an impressive level of photorealism, they enable the creation of text-based visual content, opening up new and exciting opportunities in many different application fields, from arts to video games. On the other hand, this property is an additional asset in the hands of malicious users, who can generate and distribute fake media perfectly adapted to their attacks, posing new challenges to the media forensic community. With this work, we seek to understand how difficult it is to distinguish synthetic images generated by diffusion models from pristine ones and whether current state-of-the-art detectors are suitable for the task. To this end, first we expose the forensics traces left by diffusion models, then study how current detectors, developed for GAN-generated images, perform on these new synthetic images, especially in challenging social-networks scenarios involving image compression and resizing. Datasets and code are available at github.com/grip-unina/DMimageDetection.
State-of-the-art face recognition systems require huge amounts of labeled training data. Given the priority of privacy in face recognition applications, the data is limited to celebrity web crawls, which have issues such as skewed distributions of ethnicities and limited numbers of identities. On the other hand, the self-supervised revolution in the industry motivates research on adaptation of the related techniques to facial recognition. One of the most popular practical tricks is to augment the dataset by the samples drawn from the high-resolution high-fidelity models (e.g. StyleGAN-like), while preserving the identity. We show that a simple approach based on fine-tuning an encoder for StyleGAN allows to improve upon the state-of-the-art facial recognition and performs better compared to training on synthetic face identities. We also collect large-scale unlabeled datasets with controllable ethnic constitution -- AfricanFaceSet-5M (5 million images of different people) and AsianFaceSet-3M (3 million images of different people) and we show that pretraining on each of them improves recognition of the respective ethnicities (as well as also others), while combining all unlabeled datasets results in the biggest performance increase. Our self-supervised strategy is the most useful with limited amounts of labeled training data, which can be beneficial for more tailored face recognition tasks and when facing privacy concerns. Evaluation is provided based on a standard RFW dataset and a new large-scale RB-WebFace benchmark.
Manipulation tools that realistically edit images are widely available, making it easy for anyone to create and spread misinformation. In an attempt to fight fake news, forgery detection and localization methods were designed. However, existing methods struggle to accurately reveal manipulations found in images on the internet, i.e., in the wild. That is because the type of forgery is typically unknown, in addition to the tampering traces being damaged by recompression. This paper presents Comprint, a novel forgery detection and localization method based on the compression fingerprint or comprint. It is trained on pristine data only, providing generalization to detect different types of manipulation. Additionally, we propose a fusion of Comprint with the state-of-the-art Noiseprint, which utilizes a complementary camera model fingerprint. We carry out an extensive experimental analysis and demonstrate that Comprint has a high level of accuracy on five evaluation datasets that represent a wide range of manipulation types, mimicking in-the-wild circumstances. Most notably, the proposed fusion significantly outperforms state-of-the-art reference methods. As such, Comprint and the fusion Comprint+Noiseprint represent a promising forensics tool to analyze in-the-wild tampered images.
Thanks to recent advances in deep learning, sophisticated generation tools exist, nowadays, that produce extremely realistic synthetic speech. However, malicious uses of such tools are possible and likely, posing a serious threat to our society. Hence, synthetic voice detection has become a pressing research topic, and a large variety of detection methods have been recently proposed. Unfortunately, they hardly generalize to synthetic audios generated by tools never seen in the training phase, which makes them unfit to face real-world scenarios. In this work, we aim at overcoming this issue by proposing a new detection approach that leverages only the biometric characteristics of the speaker, with no reference to specific manipulations. Since the detector is trained only on real data, generalization is automatically ensured. The proposed approach can be implemented based on off-the-shelf speaker verification tools. We test several such solutions on three popular test sets, obtaining good performance, high generalization ability, and high robustness to audio impairment.
Face manipulation technology is advancing very rapidly, and new methods are being proposed day by day. The aim of this work is to propose a deepfake detector that can cope with the wide variety of manipulation methods and scenarios encountered in the real world. Our key insight is that each person has specific biometric characteristics that a synthetic generator cannot likely reproduce. Accordingly, we extract high-level audio-visual biometric features which characterize the identity of a person, and use them to create a person-of-interest (POI) deepfake detector. We leverage a contrastive learning paradigm to learn the moving-face and audio segments embeddings that are most discriminative for each identity. As a result, when the video and/or audio of a person is manipulated, its representation in the embedding space becomes inconsistent with the real identity, allowing reliable detection. Training is carried out exclusively on real talking-face videos, thus the detector does not depend on any specific manipulation method and yields the highest generalization ability. In addition, our method can detect both single-modality (audio-only, video-only) and multi-modality (audio-video) attacks, and is robust to low-quality or corrupted videos by building only on high-level semantic features. Experiments on a wide variety of datasets confirm that our method ensures a SOTA performance, with an average improvement in terms of AUC of around 3%, 10%, and 7% for high-quality, low quality and attacked videos, respectively.
The ever higher quality and wide diffusion of fake images have spawn a quest for reliable forensic tools. Many GAN image detectors have been proposed, recently. In real world scenarios, however, most of them show limited robustness and generalization ability. Moreover, they often rely on side information not available at test time, that is, they are not universal. We investigate these problems and propose a new GAN image detector based on a limited sub-sampling architecture and a suitable contrastive learning paradigm. Experiments carried out in challenging conditions prove the proposed method to be a first step towards universal GAN image detection, ensuring also good robustness to common image impairments, and good generalization to unseen architectures.
The widespread diffusion of synthetically generated content is a serious threat that needs urgent countermeasures. The generation of synthetic content is not restricted to multimedia data like videos, photographs, or audio sequences, but covers a significantly vast area that can include biological images as well, such as western-blot and microscopic images. In this paper, we focus on the detection of synthetically generated western-blot images. Western-blot images are largely explored in the biomedical literature and it has been already shown how these images can be easily counterfeited with few hope to spot manipulations by visual inspection or by standard forensics detectors. To overcome the absence of a publicly available dataset, we create a new dataset comprising more than 14K original western-blot images and 18K synthetic western-blot images, generated by three different state-of-the-art generation methods. Then, we investigate different strategies to detect synthetic western blots, exploring binary classification methods as well as one-class detectors. In both scenarios, we never exploit synthetic western-blot images at training stage. The achieved results show that synthetically generated western-blot images can be spot with good accuracy, even though the exploited detectors are not optimized over synthetic versions of these scientific images.
The advent of deep learning has brought a significant improvement in the quality of generated media. However, with the increased level of photorealism, synthetic media are becoming hardly distinguishable from real ones, raising serious concerns about the spread of fake or manipulated information over the Internet. In this context, it is important to develop automated tools to reliably and timely detect synthetic media. In this work, we analyze the state-of-the-art methods for the detection of synthetic images, highlighting the key ingredients of the most successful approaches, and comparing their performance over existing generative architectures. We will devote special attention to realistic and challenging scenarios, like media uploaded on social networks or generated by new and unseen architectures, analyzing the impact of suitable augmentation and training strategies on the detectors' generalization ability.