485 citations · 833 across the 27 of their papers we have counts for
29 papers
Understanding Why Foundation Models Work for Diffusion-Generated Image Detection
Davide Cozzolino, Giovanni Poggi, Luisa Verdoliva
Vision foundation models have recently emerged as powerful feature extractors for detecting AI-generated images, achieving strong generalization across generators and robustness to…
Zero-Shot Detection of AI-Generated Images
Davide Cozzolino, Giovanni Poggi, Matthias Nießner +1
Detecting AI-generated images has become an extraordinarily difficult challenge as new generative architectures emerge on a daily basis with more and more capabilities and unpreced…
Exploring the Adversarial Robustness of CLIP for AI-generated Image Detection
Vincenzo De Rosa, Fabrizio Guillaro, Giovanni Poggi +2
In recent years, many forensic detectors have been proposed to detect AI-generated images and prevent their use for malicious purposes. Convolutional neural networks (CNNs) have lo…
Training-Free Deepfake Voice Recognition by Leveraging Large-Scale Pre-Trained Models
Alessandro Pianese, Davide Cozzolino, Giovanni Poggi +1
Generalization is a main issue for current audio deepfake detectors, which struggle to provide reliable results on out-of-distribution data. Given the speed at which more and more…
Synthetic Image Verification in the Era of Generative AI: What Works and What Isn't There Yet
Diangarti Tariang, Riccardo Corvi, Davide Cozzolino +3
In this work we present an overview of approaches for the detection and attribution of synthetic images and highlight their strengths and weaknesses. We also point out and discuss…
Raising the Bar of AI-generated Image Detection with CLIP
Davide Cozzolino, Giovanni Poggi, Riccardo Corvi +2
The aim of this work is to explore the potential of pre-trained vision-language models (VLMs) for universal detection of AI-generated images. We develop a lightweight detection str…
M3Dsynth: A dataset of medical 3D images with AI-generated local manipulations
Giada Zingarini, Davide Cozzolino, Riccardo Corvi +2
The ability to detect manipulated visual content is becoming increasingly important in many application fields, given the rapid advances in image synthesis methods. Of particular c…
A full-resolution training framework for Sentinel-2 image fusion
Matteo Ciotola, Mario Ragosta, Giovanni Poggi +1
This work presents a new unsupervised framework for training deep learning models for super-resolution of Sentinel-2 images by fusion of its 10-m and 20-m bands. The proposed schem…
Unsupervised Deep Learning-based Pansharpening with Jointly-Enhanced Spectral and Spatial Fidelity
Matteo Ciotola, Giovanni Poggi, Giuseppe Scarpa
In latest years, deep learning has gained a leading role in the pansharpening of multiresolution images. Given the lack of ground truth data, most deep learning-based methods carry…
Intriguing properties of synthetic images: from generative adversarial networks to diffusion models
Riccardo Corvi, Davide Cozzolino, Giovanni Poggi +2
Detecting fake images is becoming a major goal of computer vision. This need is becoming more and more pressing with the continuous improvement of synthesis methods based on Genera…
On the detection of synthetic images generated by diffusion models
Riccardo Corvi, Davide Cozzolino, Giada Zingarini +3
Over the past decade, there has been tremendous progress in creating synthetic media, mainly thanks to the development of powerful methods based on generative adversarial networks…
Deepfake audio detection by speaker verification
Alessandro Pianese, Davide Cozzolino, Giovanni Poggi +1
Thanks to recent advances in deep learning, sophisticated generation tools exist, nowadays, that produce extremely realistic synthetic speech. However, malicious uses of such tools…
Towards Universal GAN Image Detection
Davide Cozzolino, Diego Gragnaniello, Giovanni Poggi +1
The ever higher quality and wide diffusion of fake images have spawn a quest for reliable forensic tools. Many GAN image detectors have been proposed, recently. In real world scena…
Pansharpening by convolutional neural networks in the full resolution framework
Matteo Ciotola, Sergio Vitale, Antonio Mazza +2
In recent years, there has been a growing interest in deep learning-based pansharpening. Thus far, research has mainly focused on architectures. Nonetheless, model training is an e…
Are GAN generated images easy to detect? A critical analysis of the state-of-the-art
Diego Gragnaniello, Davide Cozzolino, Francesco Marra +2
The advent of deep learning has brought a significant improvement in the quality of generated media. However, with the increased level of photorealism, synthetic media are becoming…
Deep Learning Methods For Synthetic Aperture Radar Image Despeckling: An Overview Of Trends And Perspectives
Giulia Fracastoro, Enrico Magli, Giovanni Poggi +3
Synthetic aperture radar (SAR) images are affected by a spatially-correlated and signal-dependent noise called speckle, which is very severe and may hinder image exploitation. Desp…
Deep learning in the ultrasound evaluation of neonatal respiratory status
Michela Gravina, Diego Gragnaniello, Luisa Verdoliva +9
Lung ultrasound imaging is reaching growing interest from the scientific community. On one side, thanks to its harmlessness and high descriptive power, this kind of diagnostic imag…
Combining PRNU and noiseprint for robust and efficient device source identification
Davide Cozzolino, Francesco Marra, Diego Gragnaniello +2
PRNU-based image processing is a key asset in digital multimedia forensics. It allows for reliable device identification and effective detection and localization of image forgeries…
A Full-Image Full-Resolution End-to-End-Trainable CNN Framework for Image Forgery Detection
Francesco Marra, Diego Gragnaniello, Luisa Verdoliva +1
Due to limited computational and memory resources, current deep learning models accept only rather small images in input, calling for preliminary image resizing. This is not a prob…
Perceptual Quality-preserving Black-Box Attack against Deep Learning Image Classifiers
Diego Gragnaniello, Francesco Marra, Giovanni Poggi +1
Deep neural networks provide unprecedented performance in all image classification problems, taking advantage of huge amounts of data available for training. Recent studies, howeve…
Do GANs leave artificial fingerprints?
Francesco Marra, Diego Gragnaniello, Luisa Verdoliva +1
In the last few years, generative adversarial networks (GAN) have shown tremendous potential for a number of applications in computer vision and related fields. With the current pa…
Guided patch-wise nonlocal SAR despeckling
Sergio Vitale, Davide Cozzolino, Giuseppe Scarpa +2
We propose a new method for SAR image despeckling which leverages information drawn from co-registered optical imagery. Filtering is performed by plain patch-wise nonlocal means, o…
Analysis of adversarial attacks against CNN-based image forgery detectors
Diego Gragnaniello, Francesco Marra, Giovanni Poggi +1
With the ubiquitous diffusion of social networks, images are becoming a dominant and powerful communication channel. Not surprisingly, they are also increasingly subject to manipul…
Autoencoder with recurrent neural networks for video forgery detection
Dario D'Avino, Davide Cozzolino, Giovanni Poggi +1
Video forgery detection is becoming an important issue in recent years, because modern editing software provide powerful and easy-to-use tools to manipulate videos. In this paper w…