Giulia Boato

Andrea Montibeller, Cecilia Pasquini, Giulia Boato et al.

Video stabilization is an in-camera processing commonly applied by modern acquisition devices. While significantly improving the visual quality of the resulting videos, it has been shown that such operation typically hinders the forensic analysis of video signals. In fact, the correct identification of the acquisition source usually based on Photo Response non-Uniformity (PRNU) is subject to the estimation of the transformation applied to each frame in the stabilization phase. A number of techniques have been proposed for dealing with this problem, which however typically suffer from a high computational burden due to the grid search in the space of inversion parameters. Our work attempts to alleviate these shortcomings by exploiting the parallelization capabilities of Graphics Processing Units (GPUs), typically used for deep learning applications, in the framework of stabilised frames inversion. Moreover, we propose to exploit SIFT features {to estimate the camera momentum and} %to identify less stabilized temporal segments, thus enabling a more accurate identification analysis, and to efficiently initialize the frame-wise parameter search of consecutive frames. Experiments on a consolidated benchmark dataset confirm the effectiveness of the proposed approach in reducing the required computational time and improving the source identification accuracy. {The code is available at \url{https://github.com/AMontiB/GPU-PRNU-SIFT}}.

Irene Amerini, Mauro Barni, Sebastiano Battiato et al.

AI-generated synthetic media, also called Deepfakes, have significantly influenced so many domains, from entertainment to cybersecurity. Generative Adversarial Networks (GANs) and Diffusion Models (DMs) are the main frameworks used to create Deepfakes, producing highly realistic yet fabricated content. While these technologies open up new creative possibilities, they also bring substantial ethical and security risks due to their potential misuse. The rise of such advanced media has led to the development of a cognitive bias known as Impostor Bias, where individuals doubt the authenticity of multimedia due to the awareness of AI's capabilities. As a result, Deepfake detection has become a vital area of research, focusing on identifying subtle inconsistencies and artifacts with machine learning techniques, especially Convolutional Neural Networks (CNNs). Research in forensic Deepfake technology encompasses five main areas: detection, attribution and recognition, passive authentication, detection in realistic scenarios, and active authentication. This paper reviews the primary algorithms that address these challenges, examining their advantages, limitations, and future prospects.

Pietro Bongini, Sara Mandelli, Andrea Montibeller et al.

Synthetic image source attribution is an open challenge, with an increasing number of image generators being released yearly. The complexity and the sheer number of available generative techniques, as well as the scarcity of high-quality open source datasets of diverse nature for this task, make training and benchmarking synthetic image source attribution models very challenging. WILD is a new in-the-Wild Image Linkage Dataset designed to provide a powerful training and benchmarking tool for synthetic image attribution models. The dataset is built out of a closed set of 10 popular commercial generators, which constitutes the training base of attribution models, and an open set of 10 additional generators, simulating a real-world in-the-wild scenario. Each generator is represented by 1,000 images, for a total of 10,000 images in the closed set and 10,000 images in the open set. Half of the images are post-processed with a wide range of operators. WILD allows benchmarking attribution models in a wide range of tasks, including closed and open set identification and verification, and robust attribution with respect to post-processing and adversarial attacks. Models trained on WILD are expected to benefit from the challenging scenario represented by the dataset itself. Moreover, an assessment of seven baseline methodologies on closed and open set attribution is presented, including robustness tests with respect to post-processing.

Chiara Musso, Joy Battocchio, Andrea Montibeller et al.

As AI-generated synthetic images become increasingly realistic, Vision Transformers (ViTs) have emerged as a cornerstone of modern deepfake detection. However, the prevailing reliance on frozen, pre-trained backbones introduces a subtle yet critical vulnerability. In this work, we present the Surrogate Iterative Adversarial Attack (SIAA), a gray-box attack that exploits knowledge of the detector's ViT backbone alone and operates entirely within the target detector's feature space to craft highly effective adversarial examples. Through our experiments, involving multiple ViT-based detectors and diverse gray-box scenarios, including few-shot learning, complete training misalignment and attack transferability tests, we demonstrate that this vulnerability consistently yields high attack success rates, often approaching white-box performance. By doing so, we reveal that backbone knowledge alone is sufficient to undermine detector reliability, highlighting the urgent need for more resilient defenses in adversarial multimedia forensics.

Giulia Boato, Andrea Montibeller, Edward Delp et al.

AI is reshaping the landscape of multimedia forensics. We propose AI forensic agents: reliable orchestrators that select and combine forensic detectors, identify provenance and context, and provide uncertainty-aware assessments. We highlight pitfalls in current solutions and introduce a unified framework to improve the authenticity verification process.

Joy Battocchio, Stefano Dell'Anna, Andrea Montibeller et al.

Recent advancements in AI-based multimedia generation have enabled the creation of hyper-realistic images and videos, raising concerns about their potential use in spreading misinformation. The widespread accessibility of generative techniques, which allow for the production of fake multimedia from prompts or existing media, along with their continuous refinement, underscores the urgent need for highly accurate and generalizable AI-generated media detection methods, underlined also by new regulations like the European Digital AI Act. In this paper, we draw inspiration from Vision Transformer (ViT)-based fake image detection and extend this idea to video. We propose an {original} %innovative framework that effectively integrates ViT embeddings over time to enhance detection performance. Our method shows promising accuracy, generalization, and few-shot learning capabilities across a new, large and diverse dataset of videos generated using five open source generative techniques from the state-of-the-art, as well as a separate dataset containing videos produced by proprietary generative methods.

Stefano Dell'Anna, Andrea Montibeller, Giulia Boato

AI-generated synthetic media are increasingly used in real-world scenarios, often with the purpose of spreading misinformation and propaganda through social media platforms, where compression and other processing can degrade fake detection cues. Currently, many forensic tools fail to account for these in-the-wild challenges. In this work, we introduce TrueFake, a large-scale benchmarking dataset of 600,000 images including top notch generative techniques and sharing via three different social networks. This dataset allows for rigorous evaluation of state-of-the-art fake image detectors under very realistic and challenging conditions. Through extensive experimentation, we analyze how social media sharing impacts detection performance, and identify current most effective detection and training strategies. Our findings highlight the need for evaluating forensic models in conditions that mirror real-world use.

Andrea Montibeller, Dasara Shullani, Daniele Baracchi et al.

The growing presence of AI-generated videos on social networks poses new challenges for deepfake detection, as detectors trained under controlled conditions often fail to generalize to real-world scenarios. A key factor behind this gap is the aggressive, proprietary compression applied by platforms like YouTube and Facebook, which launder low-level forensic cues. However, replicating these transformations at scale is difficult due to API limitations and data-sharing constraints. For these reasons, we propose a first framework that emulates the video sharing pipelines of social networks by estimating compression and resizing parameters from a small set of uploaded videos. These parameters enable a local emulator capable of reproducing platform-specific artifacts on large datasets without direct API access. Experiments on FaceForensics++ videos shared via social networks demonstrate that our emulated data closely matches the degradation patterns of real uploads. Furthermore, detectors fine-tuned on emulated videos achieve comparable performance to those trained on actual shared media. Our approach offers a scalable and practical solution for bridging the gap between lab-based training and real-world deployment of deepfake detectors, particularly in the underexplored domain of compressed video content.

Sebastiano Verde, Cecilia Pasquini, Federica Lago et al.

The amount of multimedia content shared everyday, combined with the level of realism reached by recent fake-generating technologies, threatens to impair the trustworthiness of online information sources. The process of uploading and sharing data tends to hinder standard media forensic analyses, since multiple re-sharing steps progressively hide the traces of past manipulations. At the same time though, new traces are introduced by the platforms themselves, enabling the reconstruction of the sharing history of digital objects, with possible applications in information flow monitoring and source identification. In this work, we propose a supervised framework for the reconstruction of image sharing chains on social media platforms. The system is structured as a cascade of backtracking blocks, each of them tracing back one step of the sharing chain at a time. Blocks are designed as ensembles of classifiers trained to analyse the input image independently from one another by leveraging different feature representations that describe both content and container of the media object. Individual decisions are then properly combined by a late fusion strategy. Results highlight the advantages of employing multiple clues, which allow accurately tracing back up to three steps along the sharing chain.

Federica Lago, Cecilia Pasquini, Rainer Böhme et al.

Deep fakes became extremely popular in the last years, also thanks to their increasing realism. Therefore, there is the need to measures human's ability to distinguish between real and synthetic face images when confronted with cutting-edge creation technologies. We describe the design and results of a perceptual experiment we have conducted, where a wide and diverse group of volunteers has been exposed to synthetic face images produced by state-of-the-art Generative Adversarial Networks (namely, PG-GAN, StyleGAN, StyleGAN2). The experiment outcomes reveal how strongly we should call into question our human ability to discriminate real faces from synthetic ones generated through modern AI.

Mattia Bonomi, Cecilia Pasquini, Giulia Boato

The creation of manipulated multimedia content involving human characters has reached in the last years unprecedented realism, calling for automated techniques to expose synthetically generated faces in images and videos. This work explores the analysis of spatio-temporal texture dynamics of the video signal, with the goal of characterizing and distinguishing real and fake sequences. We propose to build a binary decision on the joint analysis of multiple temporal segments and, in contrast to previous approaches, to exploit the textural dynamics of both the spatial and temporal dimensions. This is achieved through the use of Local Derivative Patterns on Three Orthogonal Planes (LDP-TOP), a compact feature representation known to be an important asset for the detection of face spoofing attacks. Experimental analyses on state-of-the-art datasets of manipulated videos show the discriminative power of such descriptors in separating real and fake sequences, and also identifying the creation method used. Linear Support Vector Machines (SVMs) are used which, despite the lower complexity, yield comparable performance to previously proposed deep models for fake content detection.

Francesco Marra, Cristiano Saltori, Giulia Boato et al.

Current developments in computer vision and deep learning allow to automatically generate hyper-realistic images, hardly distinguishable from real ones. In particular, human face generation achieved a stunning level of realism, opening new opportunities for the creative industry but, at the same time, new scary scenarios where such content can be maliciously misused. Therefore, it is essential to develop innovative methodologies to automatically tell apart real from computer generated multimedia, possibly able to follow the evolution and continuous improvement of data in terms of quality and realism. In the last few years, several deep learning-based solutions have been proposed for this problem, mostly based on Convolutional Neural Networks (CNNs). Although results are good in controlled conditions, it is not clear how such proposals can adapt to real-world scenarios, where learning needs to continuously evolve as new types of generated data appear. In this work, we tackle this problem by proposing an approach based on incremental learning for the detection and classification of GAN-generated images. Experiments on a dataset comprising images generated by several GAN-based architectures show that the proposed method is able to correctly perform discrimination when new GANs are presented to the network

Quoc-Tin Phan, Michele Vascotto, Giulia Boato

Hue modification is the adjustment of hue property on color images. Conducting hue modification on an image is trivial, and it can be abused to falsify opinions of viewers. Since shapes, edges or textural information remains unchanged after hue modification, this type of manipulation is relatively hard to be detected and localized. Since small patches inherit the same Color Filter Array (CFA) configuration and demosaicing, any distortion made by local hue modification can be detected by patch matching within the same image. In this paper, we propose to localize hue modification by means of a Siamese neural network specifically designed for matching two inputs. By crafting the network outputs, we are able to form a heatmap which potentially highlights malicious regions. Our proposed method deals well not only with uncompressed images but also with the presence of JPEG compression, an operation usually hindering the exploitation of CFA and demosaicing artifacts. Experimental evidences corroborate the effectiveness of the proposed method.

Quoc-Tin Phan, Giulia Boato, Francesco G. B. De Natale

Clustering images according to their acquisition devices is a well-known problem in multimedia forensics, which is typically faced by means of camera Sensor Pattern Noise (SPN). Such an issue is challenging since SPN is a noise-like signal, hard to be estimated and easy to be attenuated or destroyed by many factors. Moreover, the high dimensionality of SPN hinders large-scale applications. Existing approaches are typically based on the correlation among SPNs in the pixel domain, which might not be able to capture intrinsic data structure in union of vector subspaces. In this paper, we propose an accurate clustering framework, which exploits linear dependencies among SPNs in their intrinsic vector subspaces. Such dependencies are encoded under sparse representations which are obtained by solving a LASSO problem with non-negativity constraint. The proposed framework is highly accurate in number of clusters estimation and image association. Moreover, our framework is scalable to the number of images and robust against double JPEG compression as well as the presence of outliers, owning big potential for real-world applications. Experimental results on Dresden and Vision database show that our proposed framework can adapt well to both medium-scale and large-scale contexts, and outperforms state-of-the-art methods.