Papers
2025
Self-Supervised Sar Despeckling Using Deep Image Prior
Abstract Speckle noise produces a strong degradation in SAR images, characterized by a multiplicative model. Its removal is an important step of any processing chain exploiting such data. To perform this task, several model-based despeckling methods were proposed in the past years as well as, more recently, deep learning approaches. However, most of the latter ones need to be trained on a large number of pairs of noisy and clean images that, in the case of SAR images, can only be produced with the aid of synthetic noise.
2024
CoFFEE: A Codec-based Forensic Feature Extraction and Evaluation Software for H. 264 Videos
Abstract The forensic analysis of digital videos is becoming increasingly relevant to deal with forensic cases, propaganda, and fake news. The research community has developed numerous forensic tools to address various challenges, such as integrity verification, manipulation detection, and source characterization. Each tool exploits characteristic traces to reconstruct the video life-cycle. Among these traces, a significant source of information is provided by the specific way in which the video has been encoded.
Tiny autoencoders are effective few-shot generative model detectors
Abstract The development of generative AI techniques such as Generative Adversarial Networks and Diffusion Models has made it accessible to create images, often extremely realistic, that do not represent reality. This capability has been exploited on multiple occasions by malicious actors to spread propaganda and fake news online. To trace the origin of generated content, the multimedia forensics community has developed techniques capable of identifying the specific model used to generate the content.
Beyond the Brush: Fully-automated Crafting of Realistic Inpainted Images
Abstract The generation of partially manipulated images is rapidly becoming a significant threat to the public’s trust in online content. The proliferation of diffusion model-based tools that enable easy inpainting operations has significantly lowered the barrier to accessing these techniques. In this context, the multimedia forensics community finds itself at a disadvantage compared to attackers, as developing new localization techniques often requires the creation of large datasets, a resource-intensive process due to the necessary human effort.
Uncovering the authorship: Linking media content to social user profiles
Abstract The extensive spread of fake news on social networks is carried out by a diverse range of users, encompassing private individuals, newspapers, and organizations. With widely accessible image and video editing tools, malicious users can easily create manipulated media. They can then distribute this content through multiple fake profiles, aiming to maximize its social impact. To tackle this problem effectively, it is crucial to possess the ability to analyze shared media to identify the originators of fake news.
Continual learning for adaptive social network identification
Abstract The popularity of social networks as primary mediums for sharing visual content has made it crucial for forensic experts to identify the original platform of multimedia content. Various methods address this challenge, but the constant emergence of new platforms and updates to existing ones often render forensic tools ineffective shortly after release. This necessitates the regular updating of methods and models, which can be particularly cumbersome for techniques based on neural networks which cannot quickly adapt to new classes without sacrificing performance on previously learned ones – a phenomenon known as catastrophic forgetting.
A Codec-Based Approach for Video Life-Cycle Characterization in Social Networks
Abstract Over the past decade, the proliferation of social networks introduced new challenges in the multimedia forensic field, such as the identification of the originating platform. Significant strides have been made in the characterization of digital images, exploiting features related to the media container and content. Within the realm of videos, several efforts have been directed towards analyzing the container aspect. However, the utilization of content-based features remains limited due to the intricate nature of video encoding.
Structure matters: analyzing videos via graph neural networks for social media platform attribution
Abstract Detecting the origin of a digital video within a social network is a critical task that aids law enforcement and intelligence agencies in identifying the creators of misleading visual content. In this research, we introduce an innovative method for identifying the original social network of a video, even when the video has been altered through actions like group of frames removal and file container reconstruction. The proposed method takes advantage of the video encoding’s temporal uniformity, leveraging motion vectors to characterize the specific features associated to various social media platforms.
Towards open-world multimedia forensics through media signature encoding
Abstract In this paper we introduced a framework for the forensic analysis of multimedia in open-world settings. We exploited a siamese architecture based on denoising autoencoders to encode multiple forensic features from different domains (content- and container-based features) into a compact descriptor. The proposed method is designed to cluster media belonging to similar toolchains in the signature space. We demonstrated the effectiveness of the proposed method by analysing two meaningful experimental setups involving both digital images and videos.
2023
FloreView: an image and video dataset for forensic analysis
Abstract Linking a digital image or video to its originating device, or checking the content integrity still represent challenging forensic tasks. Even though several technologies based on metadata, file format, and sensor fingerprint have been developed to address these problems, they are frequently made obsolete by new customized acquisition pipelines implemented by manufacturers. Therefore, to assess the performance of their tools, researchers continuously need new datasets containing contents captured with recent technologies.
2022
Social network identification of laundered videos based on DCT coefficient analysis
Abstract Identifying the originating social network of a digital video is considered a relevant task to support law enforcement agencies and intelligence services in tracing producers of deceptive visual contents. Recent advances in video forensics highlighted how the structure of video containers can be extremely effective in determining the social network of provenance. However, current studies do not consider that a malicious user could easily launder the traces of the social network by rebuilding the container without transcoding.
2021
Camera Obscura: exploiting in-camera processing for image counter forensics
Abstract For the last two decades Image Forensics has been providing an arsenal of forensic tools to detect tampered images. At the same time, anti-forensics technologies kept evolving to mislead forensic detectors. Such attacks are generally designed to affect a single forensic trace (e.g. JPEG compression, sensor patter noise, histogram statistics) without considering that the image alteration can negatively affect other traces, thus making harder to mimic multiple statistics of natural images.
2020
Facing image source attribution on iPhone X
Abstract Most image forensics techniques rely on the analysis of traces left into the signal during the image acquisition process, which is supposed to be common among most devices. However, recent advances in visual technologies led several manufacturers to customize the acquisition pipeline in order to improve the image quality, by designing alternative coding schemes and in-camera processing. This fact threatens the effectiveness of available forensic techniques. It is thus required to study modern acquisition devices to both assess the effectiveness of available techniques and to develop new effective approaches.
Efficient video integrity analysis through container characterization
Abstract Most video forensic techniques look for traces within the data stream that are, however, mostly ineffective when dealing with strongly compressed or low resolution videos. Recent research highlighted that useful forensic traces are also left in the video container structure, thus offering the opportunity to understand the life-cycle of a video file without looking at the media stream itself. In this paper we introduce a container-based method to identify the software used to perform a video manipulation and, in most cases, the operating system of the source device.