227 citations · 341 across the 46 of their papers we have counts for
15 papers · 1 filter
Of-SemWat: High-payload text embedding for semantic watermarking of AI-generated images with arbitrary size
Benedetta Tondi, Andrea Costanzo, Mauro Barni
We propose a high-payload image watermarking method for textual embedding, where a semantic description of the image - which may also correspond to the input text prompt-, is embed…
CycleGANWM: A CycleGAN watermarking method for ownership verification
Dongdong Lin, Benedetta Tondi, Bin Li +1
Due to the proliferation and widespread use of deep neural networks (DNN), their Intellectual Property Rights (IPR) protection has become increasingly important. This paper present…
An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defences
Wei Guo, Benedetta Tondi, Mauro Barni
Together with impressive advances touching every aspect of our society, AI technology based on Deep Neural Networks (DNN) is bringing increasing security concerns. While attacks op…
Spread-Transform Dither Modulation Watermarking of Deep Neural Network
Yue Li, Benedetta Tondi, Mauro Barni
DNN watermarking is receiving an increasing attention as a suitable mean to protect the Intellectual Property Rights associated to DNN models. Several methods proposed so far are i…
Challenging the adversarial robustness of DNNs based on error-correcting output codes
Bowen Zhang, Benedetta Tondi, Xixiang Lv +1
The existence of adversarial examples and the easiness with which they can be generated raise several security concerns with regard to deep learning systems, pushing researchers to…
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…
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…
Improving the security of Image Manipulation Detection through One-and-a-half-class Multiple Classification
Mauro Barni, Ehsan Nowroozi, Benedetta Tondi
Protecting image manipulation detectors against perfect knowledge attacks requires the adoption of detector architectures which are intrinsically difficult to attack. In this paper…
On the Transferability of Adversarial Examples Against CNN-Based Image Forensics
Mauro Barni, Kassem Kallas, Ehsan Nowroozi +1
Recent studies have shown that Convolutional Neural Networks (CNN) are relatively easy to attack through the generation of so-called adversarial examples. Such vulnerability also a…
CNN-Based Detection of Generic Constrast Adjustment with JPEG Post-processing
Mauro Barni, Andrea Costanzo, Ehsan Nowroozi +1
Detection of contrast adjustments in the presence of JPEG postprocessing is known to be a challenging task. JPEG post processing is often applied innocently, as JPEG is the most co…
An Improved Statistic for the Pooled Triangle Test against PRNU-Copy Attack
Mauro Barni, Hector Santoyo Garcia, Benedetta Tondi
We propose a new statistic to improve the pooled version of the triangle test used to combat the fingerprint-copy counter-forensic attack against PRNU-based camera identification […
Secure Detection of Image Manipulation by means of Random Feature Selection
Zhipeng Chen, Benedetta Tondi, Xiaolong Li +3
We address the problem of data-driven image manipulation detection in the presence of an attacker with limited knowledge about the detector. Specifically, we assume that the attack…
Aligned and Non-Aligned Double JPEG Detection Using Convolutional Neural Networks
Mauro Barni, Luca Bondi, Nicolò Bonettini +5
Due to the wide diffusion of JPEG coding standard, the image forensic community has devoted significant attention to the development of double JPEG (DJPEG) compression detectors th…
Adversarial Source Identification Game with Corrupted Training
Mauro Barni, Benedetta Tondi
We study a variant of the source identification game with training data in which part of the training data is corrupted by an attacker. In the addressed scenario, the defender aims…