B
Battista Biggio
Researcher at University of Cagliari
Publications - 160
Citations - 12571
Battista Biggio is an academic researcher from University of Cagliari. The author has contributed to research in topics: Malware & Computer science. The author has an hindex of 43, co-authored 140 publications receiving 9638 citations. Previous affiliations of Battista Biggio include University of Amsterdam & University of Pisa.
Papers
More filters
Book ChapterDOI
Evasion attacks against machine learning at test time
Battista Biggio,Igino Corona,Davide Maiorca,Blaine Nelson,Nedim Srndic,Pavel Laskov,Giorgio Giacinto,Fabio Roli +7 more
TL;DR: This work presents a simple but effective gradient-based approach that can be exploited to systematically assess the security of several, widely-used classification algorithms against evasion attacks.
Book ChapterDOI
Evasion Attacks against Machine Learning at Test Time
Battista Biggio,Igino Corona,Davide Maiorca,Blaine Nelson,Nedim Srndic,Pavel Laskov,Giorgio Giacinto,Fabio Roli +7 more
TL;DR: In this paper, the authors present a simple but effective gradient-based approach that can be exploited to systematically assess the security of several, widely-used classification algorithms against evasion attacks.
Proceedings Article
Poisoning Attacks against Support Vector Machines
TL;DR: In this paper, the authors investigate a family of poisoning attacks against Support Vector Machines (SVM) and demonstrate that an intelligent adversary can predict the change of the SVM's decision function due to malicious input and use this ability to construct malicious data.
Posted Content
Poisoning Attacks against Support Vector Machines
TL;DR: It is demonstrated that an intelligent adversary can, to some extent, predict the change of the SVM's decision function due to malicious input and use this ability to construct malicious data.
Proceedings ArticleDOI
Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
Battista Biggio,Fabio Roli +1 more
TL;DR: A thorough overview of the evolution of this research area over the last ten years and beyond is provided, starting from pioneering, earlier work on the security of non-deep learning algorithms up to more recent work aimed to understand the security properties of deep learning algorithms, in the context of computer vision and cybersecurity tasks.