227 citations · 275 across the 27 of their papers we have counts for
7 papers · 1 filter
Copy Move Source-Target Disambiguation through Multi-Branch CNNs
Mauro Barni, Quoc-Tin Phan, Benedetta Tondi
We propose a method to identify the source and target regions of a copy-move forgery so allow a correct localisation of the tampered area. First, we cast the problem into a hypothe…
Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples
Mauro Barni, Ehsan Nowroozi, Benedetta Tondi +1
We investigate if the random feature selection approach proposed in [1] to improve the robustness of forensic detectors to targeted attacks, can be extended to detectors based on d…
Attacking CNN-based anti-spoofing face authentication in the physical domain
Bowen Zhang, Benedetta Tondi, Mauro Barni
In this paper, we study the vulnerability of anti-spoofing methods based on deep learning against adversarial perturbations. We first show that attacking a CNN-based anti-spoofing…
Primary quantization matrix estimation of double compressed JPEG images via CNN
Yakun Niu, Benedetta Tondi, Yao Zhao +1
Available model-based techniques for the estimation of the primary quantization matrix in double-compressed JPEG images work only under specific conditions regarding the relationsh…
CNN-based Steganalysis and Parametric Adversarial Embedding: a Game-Theoretic Framework
Xiaoyu Shi, Benedetta Tondi, Bin Li +1
CNN-based steganalysis has recently achieved very good performance in detecting content-adaptive steganography. At the same time, recent works have shown that, by adopting an appro…
A new Backdoor Attack in CNNs by training set corruption without label poisoning
Mauro Barni, Kassem Kallas, Benedetta Tondi
Backdoor attacks against CNNs represent a new threat against deep learning systems, due to the possibility of corrupting the training set so to induce an incorrect behaviour at tes…