no code implementations • 24 Apr 2024 • Orazio Pontorno, Luca Guarnera, Sebastiano Battiato
The scientific community is working to develop approaches that can discriminate the origin of digital images (real or AI-generated).
no code implementations • 3 Feb 2024 • Orazio Pontorno, Luca Guarnera, Sebastiano Battiato
Deepfakes represent one of the toughest challenges in the world of Cybersecurity and Digital Forensics, especially considering the high-quality results obtained with recent generative AI-based solutions.
1 code implementation • 17 Jan 2024 • Giovanni Pasqualino, Luca Guarnera, Alessandro Ortis, Sebastiano Battiato
The progress in generative models, particularly Generative Adversarial Networks (GANs), opened new possibilities for image generation but raised concerns about potential malicious uses, especially in sensitive areas like medical imaging.
no code implementations • 9 Jan 2024 • Eleonora Breci, Luca Guarnera, Sebastiano Battiato
Preliminary results on the proposed datasets show that 90% classification accuracy can be achieved on the first subset (documents written on both paper and pen and later digitized and on tablets) and 96% on the second portion of the data.
no code implementations • 24 Dec 2023 • Mirko Casu, Luca Guarnera, Pasquale Caponnetto, Sebastiano Battiato
This paper provides a comprehensive analysis of cognitive biases in forensics and digital forensics, examining their implications for decision-making processes in these fields.
no code implementations • 17 Oct 2023 • Eleonora Breci, Luca Guarnera, Sebastiano Battiato
Handwritten document analysis is an area of forensic science, with the goal of establishing authorship of documents through examination of inherent characteristics.
no code implementations • 17 Oct 2023 • Luca Guarnera, Salvatore Manganello, Sebastiano Battiato
A new algorithm for the detection of deepfakes in digital videos is presented.
1 code implementation • 25 Jul 2023 • Roberto Leotta, Oliver Giudice, Luca Guarnera, Sebastiano Battiato
In this paper, a preliminary study to infer the probability of use of an artist's name in the input string of a generated image is presented.
no code implementations • 1 Mar 2023 • Luca Guarnera, Oliver Giudice, Sebastiano Battiato
The image deepfake detection task has been greatly addressed by the scientific community to discriminate real images from those generated by Artificial Intelligence (AI) models: a binary classification task.
no code implementations • 9 Apr 2022 • Luca Guarnera, Oliver Giudice, Matthias Niessner, Sebastiano Battiato
Despite recent advances in Generative Adversarial Networks (GANs), with special focus to the Deepfake phenomenon there is no a clear understanding neither in terms of explainability nor of recognition of the involved models.
no code implementations • 18 Mar 2022 • Luca Guarnera, Oliver Giudice, Sebastiano Battiato
Most recent style-transfer techniques based on generative architectures are able to obtain synthetic multimedia contents, or commonly called deepfakes, with almost no artifacts.
no code implementations • 24 Jan 2021 • Oliver Giudice, Luca Guarnera, Sebastiano Battiato
To properly contrast the Deepfake phenomenon the need to design new Deepfake detection algorithms arises; the misuse of this formidable A. I.
no code implementations • 7 Aug 2020 • Luca Guarnera, Oliver Giudice, Sebastiano Battiato
In this paper, a new approach aimed to extract a Deepfake fingerprint from images is proposed.
1 code implementation • 27 Apr 2020 • Luca Guarnera, Oliver Giudice, Cristina Nastasi, Sebastiano Battiato
One of the most terrifying phenomenon nowadays is the DeepFake: the possibility to automatically replace a person's face in images and videos by exploiting algorithms based on deep learning.
no code implementations • 22 Apr 2020 • Luca Guarnera, Oliver Giudice, Sebastiano Battiato
The Deepfake phenomenon has become very popular nowadays thanks to the possibility to create incredibly realistic images using deep learning tools, based mainly on ad-hoc Generative Adversarial Networks (GAN).