Research
Computer vision
Multimedia forensics and deepfake analysis
Machine learning and deep learning for image and video analysis
Adversarial machine learning
Deepfake video detection
Recent advances in visual media technology have led to new tools for processing and, above all, generating multimedia contents. In particular, modern AI-based technologies have provided easy-to-use tools to create extremely realistic manipulated videos. Such synthetic videos, named Deep Fakes, may constitute a serious threat to attack the reputation of public subjects or to address the general opinion on a certain event. According to this, being able to individuate this kind of fake information becomes fundamental. In this research project, new forensic techniques able to discern between fake and original video sequences are designed; unlike other state-of-the-art methods which resort to single video frames, we propose the adoption of optical flow fields and prediction error to exploit possible inter-frame dissimilarities.
Check out our deepfake detection demo presented at ICPR 2021
Multimedia Forensics
Source camera identification and platform provenance analysis
Forgery/Fake image and video detection
Adversarial forensics
110320seminar_Amerini_mediaforensics2.pdfAn overview on Multimedia Forensics and some recent trends
Smartphone sensors fingerprinting
Previous works have shown that microphones can be uniquely identified by audio recordings since physical features of the microphone components leave repeatable and distinguishable traces in the recording. This concept can be used in security applications to perform identification of a mobile phone through the built-in sensors (such as microphone). The problem is to determine an accurate but also efficient representation of the physical characteristics, which is not known a priori. There is also usually a trade-off between identification accuracy and the time requested to perform the classification. Various approaches have been used in literature ranging from the identification and application of handcrafted statistical features to the recent application of Deep Learning techniques. This project evaluates the application of different entropy measures and their suitability for microphone classification.
Join us! For collaborations and thesis please drop me an email if interested. I am looking for motivated PhD, Master (LM) and visiting students.
Publications
Visit my Google scholar profile for the most recent publications as well as the most-cited papers.
You can find a list of my publications also in Scopus and DBLP. My latest and ongoing works are available on arXiv.