Deepfake detection by analyzing convolutional traces

L Guarnera, O Giudice… - Proceedings of the IEEE …, 2020‏ - openaccess.thecvf.com
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 …

Fighting deepfake by exposing the convolutional traces on images

L Guarnera, O Giudice, S Battiato - IEEE access, 2020‏ - ieeexplore.ieee.org
Advances in Artificial Intelligence and Image Processing are changing the way people
interacts with digital images and video. Widespread mobile apps like FACEAPP make use of …

Preliminary forensics analysis of deepfake images

L Guarnera, O Giudice, C Nastasi… - 2020 AEIT international …, 2020‏ - ieeexplore.ieee.org
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 …

[HTML][HTML] CNN-based first quantization estimation of double compressed JPEG images

S Battiato, O Giudice, F Guarnera, G Puglisi - Journal of Visual …, 2022‏ - Elsevier
Multiple JPEG compressions leave artifacts in digital images: residual traces that could be
exploited in forensics investigations to recover information about the device employed for …

Exploiting AC Histogram Statistics for Misalignment Estimation in Double JPEG Compressed Images

S Battiato, F Guarnera, G Puglisi - IEEE Access, 2024‏ - ieeexplore.ieee.org
A critical task in forensics investigation is the recovery of the manipulation history of the
image under analysis. To this aim, considering a typical life-cycle of a digital image, the …

Deep forgery discriminator via image degradation analysis

M Yu, J Zhang, S Li, J Lei, F Wang… - IET Image …, 2021‏ - Wiley Online Library
Generative adversarial network‐based deep generative model is widely applied in creating
hyper‐realistic face‐swap** images and videos. However, its malicious use has posed a …

First quantization estimation by a robust data exploitation strategy of DCT coefficients

S Battiato, O Giudice, F Guarnera, G Puglisi - IEEE Access, 2021‏ - ieeexplore.ieee.org
It is well known that the JPEG compression pipeline leaves residual traces in the
compressed images that are useful for forensic investigations. Through the analysis of such …

Estimating previous quantization factors on multiple JPEG compressed images

S Battiato, O Giudice, F Guarnera, G Puglisi - EURASIP Journal on …, 2021‏ - Springer
The JPEG compression algorithm has proven to be efficient in saving storage and
preserving image quality thus becoming extremely popular. On the other hand, the overall …

Deepfake style transfer mixture: a first forensic ballistics study on synthetic images

L Guarnera, O Giudice, S Battiato - International Conference on Image …, 2022‏ - Springer
Most recent style-transfer techniques based on generative architectures are able to obtain
synthetic multimedia contents, or commonly called deepfakes, with almost no artifacts …

A robust misalignment estimation approach in non-aligned double JPEG compression scenario

G Puglisi, S Battiato - 2022 IEEE International Conference on …, 2022‏ - ieeexplore.ieee.org
The estimation of the misalignment between consecutive JPEG compressions is a really
important task that can be useful in forensics investigation for first quantization matrix …