197 research outputs found
Compressione dei dati SAR grezzi mediante focalizzazione in range e codifica a tasso variabile
No full textTesi di Dottorat
Media Forensics and DeepFakes: an overview
No full textWith the rapid progress of recent years, techniques that generate and
manipulate multimedia content can now guarantee a very advanced level of
realism. The boundary between real and synthetic media has become very thin. On
the one hand, this opens the door to a series of exciting applications in
different fields such as creative arts, advertising, film production, video
games. On the other hand, it poses enormous security threats. Software packages
freely available on the web allow any individual, without special skills, to
create very realistic fake images and videos. So-called deepfakes can be used
to manipulate public opinion during elections, commit fraud, discredit or
blackmail people. Potential abuses are limited only by human imagination.
Therefore, there is an urgent need for automated tools capable of detecting
false multimedia content and avoiding the spread of dangerous false
information. This review paper aims to present an analysis of the methods for
visual media integrity verification, that is, the detection of manipulated
images and videos. Special emphasis will be placed on the emerging phenomenon
of deepfakes and, from the point of view of the forensic analyst, on modern
data-driven forensic methods. The analysis will help to highlight the limits of
current forensic tools, the most relevant issues, the upcoming challenges, and
suggest future directions for research
Compressione dei dati SAR grezzi mediante focalizzazione in range e codifica a tasso variabile
No full textTesi di Dottorat
Multimedia Forensics Before the Deep Learning Era
No full textImage manipulation is as old as photography itself, and powerful media editing tools have been around for a long time. Using such conventional signal processing methods, it is possible to modify images and videos obtaining very realistic results. This chapter is devoted to describe the most effective strategies to detect the widespread manipulations that rely on traditional approaches and do not require a deep learning strategy. In particular, we will focus on manipulations like adding, replicating, or removing objects and present the major lines of research in multimedia forensics before the deep learning era and the rise of deepfakes. The most popular approaches look for artifacts related to the in-camera processing chain (camera-based clues) or the out-camera processing history (editing-based clues). We will focus on methods that rely on the extraction of a camera fingerprint and need some prior information on pristine data, for example, through a collection of images taken from the camera of interest. Then we will shift to blind methods that do not require any prior knowledge and reveal inconsistencies with respect to some well-defined hypotheses. We will also briefly review the most interesting features of machine learning- based methods and finally present the major challenges in this area
Camera-based image forgery localization using convolutional neural networks
No full textCamera fingerprints are precious tools for a number of image forensics tasks. A well-known example is the photo response non-uniformity (PRNU) noise pattern, a powerful device fingerprint. Here, to address the image forgery localization problem, we rely on noiseprint, a recently proposed CNN-based camera model fingerprint. The CNN is trained to minimize the distance between same-model patches, and maximize the distance otherwise. As a result, the noiseprint accounts for model-related artifacts just like the PRNU accounts for device-related non-uniformities. However, unlike the PRNU, it is only mildly affected by residuals of high-level scene content. The experiments show that the proposed noiseprint-based forgery localization method improves over the PRNU-based reference
Design of low-resolution multiple description vector quantizers by means of the self organizing maps
No full textPublication in the conference proceedings of EUSIPCO, Lausanne, Switzerland, 200
Classification-based nonlocal SAR despeckling
No full textNonlocal techniques represent the current state of the art in SAR despeckling, providing a good compromise between speckle reduction and preservation of relevant image features. Nonetheless, they are not free from problems, going from the loss of image features to the introduction of their own brand of artifacts, due to the inability to deal equally well with all types of imaged scenes. A possible tool to improve performance is a prior segmentation or classification of the image, so as to adjust the filter parameters to fit the nature of the region under analysis. This work first provides some insight into the potential of classification-based nonlocal filtering by running simulation experiments in a controlled environment. Then proposes a new version of the SAR-BM3D despeckling technique in which each pixel is first classified as homogeneous or not, and then filtered with class-adapted parameters. Although results on real SAR images are still questionable, there is already some significant gain in selected areas that justifies the interest towards this approach
Biologically-inspired dense local descriptor for indirect immunofluorescence image classification
No full text- …
