The amount of multimedia content shared everyday online recently underwent a dramatic increase. This, combined with the stunning realism of fake images that can be generated with AI-based technologies, undermines the trustworthiness of online information sources. In this work, we tackle the problem of preserving media trustworthiness online from two different points of view. The first one consists in assessing the human ability to spot fake images, focusing in particular on synthetic faces, which are extremely realistic and can represent a severe threat if used to disseminate fake news. A perception study allowed us to prove for the first time how people are more prone to question the reality of authentic pictures rather than the one of last-generation AI-generated images. Secondly, we focused on social media forensics: our goal is to reconstruct the history of an image shared or re-shared online as typically happens nowadays. We propose a new framework that is able to trace the history of an image over multiple sharings. This framework improves the state of the art and has the advantage of being easily extensible with new methods and thus adapt to new datasets and scenarios. In fact, in this environment of fast-paced technological evolution, being able to adapt is fundamental to preserve our trust in what we see.

Snapchat and BeReal are popular social media platforms focused on photo sharing and instant messaging. A tool often used in police investigations is the analysis of communication, this includes different electronic devices and smartphone devices. However, Law enforcement faces challenges when analyzing communication in police investigations due to encryption and privacy protection. The experiment included three phases: artifact production, data acquisition, and data examination & analysis. In the artifact production phase, four devices exchanged chat messages, images, and videos. The data acquisition phase involved using two licensed forensic tools, Magnet Axiom and MOBILedit Forensic PRO. The final phase involved examining and analyzing the extracted data to find artifacts that could serve as supporting evidence in criminal investigations. Several conclusions were drawn from this study. Notably, the experiment revealed diverse types of forensic artifacts. Metadata files that contained information about the applications were the most common. Examples of this were com.snapchat.android.apk and com.bereal.ft.apk for Android, and iTunesMetadata.plist together with other .plist files for iPhone. These files provide valuable data such as user information, activity, and timestamps. Important locations and key factors were also identified.