activity
20132026
most citedAligned and Non-Aligned Double JPEG Detection Using Convolutional Neural Networks

227 citations · 275 across the 27 of their papers we have counts for

collaborators
Showing 2019Show all

7 papers · 1 filter

cs.CV2019

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…

cs.CR2019

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…

cs.CR2019★ 4 cited

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…

eess.IV2019

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…

cs.MM2019

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…

cs.CR2019★ 2 cited

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…