Digital forensics and blockchain technology against deceptive deepfake images in social media
The TRUEBEES project is funded by the EU NGI Initiative Trublo, and entails a collaboration between our lab and the consulting company U-Hopper Srl.
Manipulating an image or video is becoming easier and easier. “Deepfakes”, i.e. the synthesis of the human image based on Artificial Intelligence, is a growing phenomenon today. Apart from a few examples of comedy or jokes, the scenarios opening up are alarming: scams, cyberbullying, revenge porn, computer crimes.
TrueBees will combine innovative AI digital image forensics methods with blockchain technology to guarantee that a given visual user-generated content is trustworthy and fight the diffusion of those synthetically AI-generated images (deepfakes) on social networks,.
Uncovering media manipulation chains through container and content detectable traces
The UNCHAINED project is funded by DARPA (Defense Advanced Research Program Agency) and aims at designing a reliable forensics analysis framework able to characterize signatures left by different toolchains on digital images and videos. The core technical challenge of UNCHAINED is to build an information fusion system encompassing content-based statistics, container-based characteristics and additional side information (when available), to probabilistically map the media object under analysis first into a toolchain family and then into a specific toolchain, built upon a scalable set of basic operations. This includes the detection of AI-based generation processes, as well as common operations such as sharing on social media.
UNCHAINED aims at fusing container-based and content-based cues in realistic scenarios where images and videos might undergo mixed toolchains of operations. The main objective is to create a framework able to reverse-engineer the media object to discover the associated toolchain.
Preserving media trustworthiness in the artificial intelligence era
PREMIER is a research project funded by MIUR through the PRIN 2017 program which addresses the development of new generation video forensics techniques.
Advances in Artificial Intelligence (AI) enable the creation of manipulated digital videos with unprecedented quality and minimum user intervention, empowering even non-skilled users to generate plausible fake content and potentially pursue malevolent uses. With the goal of preserving the overall dependability of digital media data, the research field of MultiMedia Forensics (MMF) develops techniques to gather information on their digital history, detect manipulations, and output indications on their authenticity. In this context, the objective of PREMIER is to devise new techniques capable of distinguishing fake from original videos. The project will develop improved MMF detectors based on deep learning, overcoming the main shortcomings of existing methodologies. PREMIER will contribute to boost video forensics technology and provide citizens with advanced publicly available tools to assess the authenticity of their own videos. Data collection of original and fake videos will be performed and updated in the course of the project, and will be made available to the international research community.
Ausilia is a running project aimed at deploying a territorial lab for the study of innovative solutions to foster independent living for elderly and disabled people. Ausilia is based on a dedicated infrastructure, designed by the University Of Trento's Engineering Departments (DISI, DII and DICAM) in collaboration with hospital staff of Villa Rosa rehabilitation hospital (Pergine Valsugana, Trento), composed of two living environments. The first one is an apartment which is a living lab where the user lives for a few days and is constantly monitored by several sensors deployed all over in the environment in order to “measure” the performance of the user in their everyday life activities. The second “space” is a gym which is composed by simulated and reconfigurable scenarios where the domestic environment is reproduced, to study the best fitting solution to the specific user problem. The lab enables medical doctors to objectively assess the patient's residual skills and at the same time to design a user-centered solution to increase the independent living capabilities of the patient (needs in terms of: technology, aids, safety, homecare, etc).
Antemotion is a local company, based in Rovereto, which started a collaboration project with the University of Trento in 2018. The project objective consists in: the development of a new simulator for the autonomous industry and the realization of an interactive VR software where a person can be immerse in a car interior environment and interact with it .
Shared.Media: the aim of the project in collaboration with StreamOut s.r.l. is to develop a video analysis system to extract automatically the best parts of the recorded video in order to generate a video highlight, with the usage of recognition algorithms and artificial intelligence. Thanks to the system the final user will receive a digital memory of its activity, such as rafting, paragliding or a tour with a supercar, and will be able to share it on social networks.
Jointly Learning Multimedia Data Security
This EUREGIO Mobility Fund initiative addresses the establishment of a new joint teaching module between the University of Trento (MeMLab) and the University of Innsbruck (SecLab), with the goal of providing students with a more complete and consistent training offer on multimedia security and forensics. In particular, the MS course "Multimedia Data Security" (6 ECTS) taught by Prof. Boato at UNITN and the MS course "Multimedia Data Security" (5 ECTS) taught by Prof. Böhme and Dr. Pasquini at UIBK have developed on a joint track, by proposing common teaching material, mutual guest lectures, and a joint event in Trento closing the cross-national student challenge organized within the course.
Humans in the Digital Era - New Opportunities and Threats for Information Security
This EUREGIO Mobility Fund initiative consists of a thematic guest lecture series in the fields of information security and multimedia signal processing. The seminars, held by internationally recognized external speakers, are open to postgraduate students participating to the research activities of the labs and/or attending the master courses offered at the respective institutions., and are jointly organized by the universities of Trento, Innsbruck, and Bolzano.
Do you trust what you see? The EUREGIO Challenge on Multimedia Security and Forensics
This EUREGIO Mobility Fund project aims at strengthening the teaching offer in the field of multimedia security and forensics by linking efforts of the University of Trento and the University of Innsbruck. Joint activities include mutual guest lectures and a cross-national student challenge.
SMARTOUR is a MIUR-PON POJECT (Smart Cities and Communities and Social Innovation (D.D. 84/Ric. del 02/03/12) - Progetti di Innovazione Sociale). Project objective is the realization of interactive territorial marketing, social and inter-operable, connecting the knowledge about the touristic areas with the community experiences as well as the promotion of the production activities with the most innovative information and communication technologies, allowing a simple fruition of the touristic and cultural facilities of a city. This interactive guide will be available also offline and connected to one or more social networks.
UNCAP (“Ubiquitous iNteroperable Care for Ageing People “) will make use of solutions and technologies developed in previous research projects to develop an open, scalable and privacy-savvy ICT infrastructure designed to help aging people live independently while maintaining and improving their lifestyle. The final solution will consist of real products that will be made available on the market. The project is co-financed by the EU through the Horizon 2020 programme, and it involves 23 partners (including several pilot user partners) from 9 European countries (IT, UK, SI, RO, EL, DE, SE, ES, MK).
The “Wireless and Optical TestBed Laboratory” (WOTBL) is a platform leveraging on the ultra-wide band project of the Autonomous Province of Trento. The facilities and basic resources that compose the TestBed include optical fiber, spaces, roaming access to the network (including wireless network), computational resources, centralized service facilities and the possibility of collaborating with experts in the field from industry, university, research and public administration.
COST COREGROUP EMOTION
MOTUS (Mobility and Tourism in Urban Scenarios) aims at improving the management, sustainability and eco-compatibility of mobility through a paradigm change which puts the citizen/tourist at the center of the system, as infomobility service user and builder. MOTUS is a platform of services able to detect, aggregate and interpret urban mobility in real time starting from information gathered on the heterogeneous infrastructures available on the road system as well as data provided by mobile devices positioned in the areas of interest. MOTUS will be able to process in an innovative way the mobility data with the goal to develop suitable traffic models to support monitoring and planning services, which will be used to plan actions for infrastructure enhancement and existing systems improvement.
The project will create a set of tools to enrich the annotation and to create multi-faceted interconnections among media contents. IHTE is executing user trials to iteratively improve the tools in a real-world setup. Two main focus areas in IHTE's work are the following: (1) multi-device interaction and (2) reliving and searching for event-based multimedia.
We describe the world using words. But words often call to mind different mental views of the world to different people, because of their differing personal experience and contexts. As a result, the semantic gap between our verbally expressed conceptualizations of the world and our actual experience of the world – which is most directly represented by media such as photos and videos – is far beyond the reach of current multimedia systems. Hence we don’t yet have a universal way of contextualizing search, navigation and media management according to users’ needs and their operating environments. A key idea underlying the Integrating Project GLOCAL is to use events as the primary means for organizing and indexing media.
Knowledge and its articulations are strongly influenced by diversity in, e.g., cultural backgrounds, schools of thought, geographical contexts. Judgements, assessments and opinions, which play a crucial role in many areas of democratic societies, including politics and economics, reflect this diversity in perspective and goals. For theinformation on the Web (including, e.g., news and blogs) diversity implied by the ever increasing multitude of information providers - is the reason for diverging viewpoints and conflicts. Time and evolution add a further dimension making diversity an intrinsic and unavoidable property of knowledge.
TRITon is a research and innovation project funded by the project members and the Autonomous Province of Trento aimed at advancing the state of the art in the management of road tunnels, specifically to improve safety and reduce energy costs. To achieve these goals, TRITon will merge research on state-of-the-art technology into the established practices of road tunnel infrastructures, supported by project members that include local research centers and companies working in the field.
An example application, central in TRITon, is adaptive lighting. In current deployments, the light intensity inside the tunnel is typically regulated based on design parameters and the current date and time, and regardless of the actual environmental conditions. As it can be experienced when driving through a road tunnel too bright or too dark, this potentially determines a waste of energy, as well as a potential safety hazard. In TRITon, the light intensity inside the tunnel will instead be regulated through a wireless sensor network (WSN). This will relay sensed light information to the control station, which will exploit such information for fine-grained adaptation to environmental condition, significantly reducing costs and improving safety.
Latest research work within ICT has allowed to pinpoint the most important and urgently required features that future systems should possess to meet users' needs. Accordingly, methods making systems capable of adapting to changes in user requirements and application domains have been pointed out as key research areas. Adaptation and evolution depend on several dimensions, e.g., time, location, and security conditions, expressing the diversity of the context in which systems operate. A design based on an effective management of these dimensions constitutes a remarkable step towards the realization of Trustworthy Eternal Systems. The EternalS Coordination Action specifically aims at coordinating research in that area based on a researcher Task Force together with community building activities, where the organization of large workshops and conferences is just one of the tools that will be used to conduct a successful CA.
ACube (Ambient-Aware Assistance) targets the design and implementation of a highly-developed smart environment to be deployed in nursing homes as a support to medical and assistance staff. In the framework of the recent technological trend Ambient Intelligence (AmI), the ACube platform addresses the quality of care, quality of life of the assisted, as well as working conditions for caregivers. Indeed, the major technical outcome of the project is an integrated, layered platform for intelligent monitoring, able to efficiently accommodate and manage a wide range of sensors and combine the acquired data into high-level perception, in a highly configurable and autonomous manner.
E-Value is a three years research project developed by The Erickson Research Center and based on several years of action-research projects and test-retest actions held in primary schools around Italy, evaluating difficulties in learning and teaching literacy and numeracy. The main objective of the E-VALUE project is to design, develop and test a multimedia platform, which integrates the evaluation of various learning cognitive abilities (metaphonology, writing, reading , calculate, etc.) with the didactic intervention in class using Learning Objects (LO) and e-books derived from the Erickson books and multimedia software catalogue.