227 citations · 994 across the 36 of their papers we have counts for
17 papers · 1 filter
H4VDM: H.264 Video Device Matching
Ziyue Xiang, Paolo Bestagini, Stefano Tubaro +1
Methods that can determine if two given video sequences are captured by the same device (e.g., mobile telephone or digital camera) can be used in many forensics tasks. In this pape…
An Overview on the Generation and Detection of Synthetic and Manipulated Satellite Images
Lydia Abady, Edoardo Daniele Cannas, Paolo Bestagini +3
Due to the reduction of technological costs and the increase of satellites launches, satellite images are becoming more popular and easier to obtain. Besides serving benevolent pur…
Splicing Detection and Localization In Satellite Imagery Using Conditional GANs
Emily R. Bartusiak, Sri Kalyan Yarlagadda, David Güera +4
The widespread availability of image editing tools and improvements in image processing techniques allow image manipulation to be very easy. Oftentimes, easy-to-use yet sophisticat…
Detecting GAN-generated Images by Orthogonal Training of Multiple CNNs
Sara Mandelli, Nicolò Bonettini, Paolo Bestagini +1
In the last few years, we have witnessed the rise of a series of deep learning methods to generate synthetic images that look extremely realistic. These techniques prove useful in…
Forensic Analysis of Synthetically Generated Western Blot Images
Sara Mandelli, Davide Cozzolino, Edoardo D. Cannas +8
The widespread diffusion of synthetically generated content is a serious threat that needs urgent countermeasures. As a matter of fact, the generation of synthetic content is not r…
Training Strategies and Data Augmentations in CNN-based DeepFake Video Detection
Luca Bondi, Edoardo Daniele Cannas, Paolo Bestagini +1
The fast and continuous growth in number and quality of deepfake videos calls for the development of reliable detection systems capable of automatically warning users on social med…
Training CNNs in Presence of JPEG Compression: Multimedia Forensics vs Computer Vision
Sara Mandelli, Nicolò Bonettini, Paolo Bestagini +1
Convolutional Neural Networks (CNNs) have proved very accurate in multiple computer vision image classification tasks that required visual inspection in the past (e.g., object reco…
FOCAL: A Forgery Localization Framework based on Video Coding Self-Consistency
Sebastiano Verde, Paolo Bestagini, Simone Milani +2
Forgery operations on video contents are nowadays within the reach of anyone, thanks to the availability of powerful and user-friendly editing software. Integrity verification and…
On the use of Benford's law to detect GAN-generated images
Nicolò Bonettini, Paolo Bestagini, Simone Milani +1
The advent of Generative Adversarial Network (GAN) architectures has given anyone the ability of generating incredibly realistic synthetic imagery. The malicious diffusion of GAN-g…
Video Face Manipulation Detection Through Ensemble of CNNs
Nicolò Bonettini, Edoardo Daniele Cannas, Sara Mandelli +3
In the last few years, several techniques for facial manipulation in videos have been successfully developed and made available to the masses (i.e., FaceSwap, deepfake, etc.). Thes…
An In-Depth Study on Open-Set Camera Model Identification
Pedro Ribeiro Mendes Júnior, Luca Bondi, Paolo Bestagini +2
Camera model identification refers to the problem of linking a picture to the camera model used to shoot it. As this might be an enabling factor in different forensic applications…
A Counter-Forensic Method for CNN-Based Camera Model Identification
David Güera, Yu Wang, Luca Bondi +3
An increasing number of digital images are being shared and accessed through websites, media, and social applications. Many of these images have been modified and are not authentic…
Reliability Map Estimation For CNN-Based Camera Model Attribution
David Güera, Sri Kalyan Yarlagadda, Paolo Bestagini +3
Among the image forensic issues investigated in the last few years, great attention has been devoted to blind camera model attribution. This refers to the problem of detecting whic…
Satellite Image Forgery Detection and Localization Using GAN and One-Class Classifier
Sri Kalyan Yarlagadda, David Güera, Paolo Bestagini +3
Current satellite imaging technology enables shooting high-resolution pictures of the ground. As any other kind of digital images, overhead pictures can also be easily forged. Howe…
Reduced Memory Region Based Deep Convolutional Neural Network Detection
Denis Tome', Luca Bondi, Emanuele Plebani +3
Accurate pedestrian detection has a primary role in automotive safety: for example, by issuing warnings to the driver or acting actively on car's brakes, it helps decreasing the pr…
Deep convolutional neural networks for pedestrian detection
Denis Tomè, Federico Monti, Luca Baroffio +3
Pedestrian detection is a popular research topic due to its paramount importance for a number of applications, especially in the fields of automotive, surveillance and robotics. De…
Fast keypoint detection in video sequences
Luca Baroffio, Matteo Cesana, Alessandro Redondi +1
A number of computer vision tasks exploit a succinct representation of the visual content in the form of sets of local features. Given an input image, feature extraction algorithms…