E
Ehsan Nowroozi
Researcher at University of Siena
Publications - 21
Citations - 323
Ehsan Nowroozi is an academic researcher from University of Siena. The author has contributed to research in topics: JPEG & Deep learning. The author has an hindex of 8, co-authored 21 publications receiving 151 citations. Previous affiliations of Ehsan Nowroozi include Shahid Beheshti University & University of Padua.
Papers
More filters
Proceedings ArticleDOI
Cnn-Based Detection of Generic Contrast Adjustment with Jpeg Post-Processing
TL;DR: In this paper, a patch-based CNN is used to distinguish pristine images from contrast adjusted images, for some selected adjustment operators of different nature, which is robust to JPEG compression.
Proceedings ArticleDOI
On the Transferability of Adversarial Examples against CNN-based Image Forensics
TL;DR: The results of several experiments show that, in the majority of the cases, the attacks are not transferable, thus easing the design of proper countermeasures at least when the attacker does not have a perfect knowledge of the target detector.
Journal ArticleDOI
A survey of machine learning techniques in adversarial image forensics
TL;DR: Techniques that can be used to enhance the robustness of machine learning-based binary manipulation detectors in various adversarial scenarios are surveyed.
Proceedings ArticleDOI
Higher-order, adversary-aware, double JPEG-detection via selected training on attacked samples
TL;DR: Experimental results prove that training on such a kind of most powerful attacks allows good detection in the presence of a much wider variety of attacks and processing.
Posted Content
CNN Detection of GAN-Generated Face Images based on Cross-Band Co-occurrences Analysis
TL;DR: This work proposes a method for distinguishing GAN-generated from natural images by exploiting inconsistencies among spectral bands, with specific focus on the generation of synthetic face images using cross-band co-occurrence matrices as input to a CNN model, which is trained to distinguish between real and synthetic faces.