P
Pavel Laskov
Researcher at University of Tübingen
Publications - 76
Citations - 9269
Pavel Laskov is an academic researcher from University of Tübingen. The author has contributed to research in topics: Intrusion detection system & Anomaly detection. The author has an hindex of 36, co-authored 69 publications receiving 7953 citations. Previous affiliations of Pavel Laskov include Huawei & University of Delaware.
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.
Book ChapterDOI
Learning and Classification of Malware Behavior
TL;DR: The effectiveness of the proposed method for learning and discrimination of malware behavior is demonstrated, especially in detecting novel instances of malware families previously not recognized by commercial anti-virus software.