Zobrazeno 1 - 10
of 1 160
pro vyhledávání: '"Tondi, P"'
Synthetic image attribution addresses the problem of tracing back the origin of images produced by generative models. Extensive efforts have been made to explore unique representations of generative models and use them to attribute a synthetic image
Externí odkaz:
http://arxiv.org/abs/2405.11491
Most of the approaches proposed so far to craft targeted adversarial examples against Deep Learning classifiers are highly suboptimal and typically rely on increasing the likelihood of the target class, thus implicitly focusing on one-hot encoding se
Externí odkaz:
http://arxiv.org/abs/2401.01199
In recent years, there has been significant growth in the commercial applications of generative models, licensed and distributed by model developers to users, who in turn use them to offer services. In this scenario, there is a need to track and iden
Externí odkaz:
http://arxiv.org/abs/2311.05478
We propose a novel multi-bit box-free watermarking method for the protection of Intellectual Property Rights (IPR) of GANs with improved robustness against white-box attacks like fine-tuning, pruning, quantization, and surrogate model attacks. The wa
Externí odkaz:
http://arxiv.org/abs/2310.16919
Autor:
Romeo Di Pietro, Safiya Praleskouskaya, Michele Aleffi, Francesco Di Pietro, Adriano Di Pietro, Giancarlo Tondi, Paola Fortini
Publikováno v:
Plant Sociology, Vol 61, Iss 2, Pp 21-40 (2024)
During a phytosociological field-work campaign aimed at studying some relict Scheuchzerio-Caricetea boreal mires of the montane and subalpine belts of the Laga Mountains, the highest and largest siliceous massif of the Apennine range, several bryophy
Externí odkaz:
https://doaj.org/article/76c7271a6a594b299c05806863f8674a
Autor:
Omran Alamayreh, Carmelo Fascella, Sara Mandelli, Benedetta Tondi, Paolo Bestagini, Mauro Barni
Publikováno v:
EURASIP Journal on Image and Video Processing, Vol 2024, Iss 1, Pp 1-23 (2024)
Abstract In the last few years, research on the detection of AI-generated videos has focused exclusively on detecting facial manipulations known as deepfakes. Much less attention has been paid to the detection of artificial non-facial fake videos. In
Externí odkaz:
https://doaj.org/article/cefe58b0005f4b639712cca245c1b0af
Despite the wide variety of methods developed for synthetic image attribution, most of them can only attribute images generated by models or architectures included in the training set and do not work with unknown architectures, hindering their applic
Externí odkaz:
http://arxiv.org/abs/2307.09822
Classification of AI-manipulated content is receiving great attention, for distinguishing different types of manipulations. Most of the methods developed so far fail in the open-set scenario, that is when the algorithm used for the manipulation is no
Externí odkaz:
http://arxiv.org/abs/2304.05212
Publikováno v:
IEEE TIFS 2023
We propose a Universal Defence against backdoor attacks based on Clustering and Centroids Analysis (CCA-UD). The goal of the defence is to reveal whether a Deep Neural Network model is subject to a backdoor attack by inspecting the training dataset.
Externí odkaz:
http://arxiv.org/abs/2301.04554
Due to the proliferation and widespread use of deep neural networks (DNN), their Intellectual Property Rights (IPR) protection has become increasingly important. This paper presents a novel model watermarking method for an unsupervised image-to-image
Externí odkaz:
http://arxiv.org/abs/2211.13737