1.4k citations · 5.5k across the 87 of their papers we have counts for
3 papers · 1 filter
AdversariaLib: An Open-source Library for the Security Evaluation of Machine Learning Algorithms Under Attack
Igino Corona, Battista Biggio, Davide Maiorca
We present AdversariaLib, an open-source python library for the security evaluation of machine learning (ML) against carefully-targeted attacks. It supports the implementation of s…
Statistical Meta-Analysis of Presentation Attacks for Secure Multibiometric Systems
Battista Biggio, Giorgio Fumera, Gian Luca Marcialis +1
Prior work has shown that multibiometric systems are vulnerable to presentation attacks, assuming that their matching score distribution is identical to that of genuine users, with…
Randomized Prediction Games for Adversarial Machine Learning
Samuel Rota Bulò, Battista Biggio, Ignazio Pillai +2
In spam and malware detection, attackers exploit randomization to obfuscate malicious data and increase their chances of evading detection at test time; e.g., malware code is typic…