Ehsan Nowroozi — accepted AI-conference papers

2020

Effectiveness of Random Deep Feature Selection for Securing Image Manipulation Detectors Against Adversarial Examples

Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang

ICASSP 2020accepted

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 deep learning features. In particular, we study the transferability of adversarial examples targeting an original CNN ima…

Cited by 0 Source ↗Scholar ↗

2019

On the Transferability of Adversarial Examples against CNN-based Image Forensics

Mauro Barni, Kassem Kallas, Ehsan Nowroozi, Benedetta Tondi

ICASSP 2019accepted

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 affects CNN-based image forensic tools. Research in deep learning has shown that adversarial examples exhibit a certain d…

Cited by 0 Source ↗Scholar ↗