PyTorch implementation of Targeted Adversarial Perturbations for Monocular Depth Predictions (in NeurIPS 2020)

AdvSV stands as the first dataset developed specifically for evaluating Speaker Verification (SV) systems against adversarial attacks. It aims to benchmark the robustness of ASV models in the face of such attacks and offers vital resources for researchers to explore the characteristics of adversarial and replay attacks in this domain.

The adversarial sample detection model based on edge noise feature

Thesis: Detecting Adversaries in DQNs and Computer Vision using Bayesian CNNs

Felice Antonio Merra's Personal Blog. Follow my research activity! @merrafelice

Paper ACTIVE-ICCV2023

Anomaly-Based Intrusion Detection System using Machine Learning (SVM & Neural Networks) on NSL-KDD and UNB-IDS 2018 datasets with adversarial robustness evaluation.

A page where I host my work on Adversarial Machine Learning