Navigation überspringen
Universitätsbibliothek Heidelberg
Standort: ---
Exemplare: ---
 Online-Ressource
Verfasst von:Labaca Castro, Raphael [VerfasserIn]   i
Titel:Machine Learning under Malware Attack
Verf.angabe:by Raphael Labaca Castro
Ausgabe:1st ed. 2023.
Verlagsort:Wiesbaden
 Wiesbaden
Verlag:Springer Fachmedien Wiesbaden
 Imprint: Springer Vieweg
E-Jahr:2023
Jahr:2023.
 2023.
Umfang:1 Online-Ressource(XXXIV, 116 p. 18 illus. Textbook for German language market.)
ISBN:978-3-658-40442-0
Abstract:The Beginnings of Adversarial ML -- Framework for Adversarial Malware Evaluation -- Problem-Space Attacks -- Feature-Space Attacks -- Closing Remarks.
 Machine learning has become key in supporting decision-making processes across a wide array of applications, ranging from autonomous vehicles to malware detection. However, while highly accurate, these algorithms have been shown to exhibit vulnerabilities, in which they could be deceived to return preferred predictions. Therefore, carefully crafted adversarial objects may impact the trust of machine learning systems compromising the reliability of their predictions, irrespective of the field in which they are deployed. The goal of this book is to improve the understanding of adversarial attacks, particularly in the malware context, and leverage the knowledge to explore defenses against adaptive adversaries. Furthermore, to study systemic weaknesses that can improve the resilience of machine learning models. About the author Raphael Labaca-Castro is a computer scientist whose primary interests lie in the nexus between Machine Learning and Computer Security. He holds a PhD in Adversarial Machine Learning and currently leads an ML team in the quantum security field. .
DOI:doi:10.1007/978-3-658-40442-0
URL:Resolving-System: https://doi.org/10.1007/978-3-658-40442-0
 DOI: https://doi.org/10.1007/978-3-658-40442-0
Schlagwörter:(s)Cyberattacke   i / (s)Maschinelles Lernen   i
Datenträger:Online-Ressource
Sprache:eng
Bibliogr. Hinweis:Erscheint auch als : Druck-Ausgabe
 Erscheint auch als : Druck-Ausgabe
K10plus-PPN:183343062X
 
 
Lokale URL UB: Zum Volltext
 
 Bibliothek der Medizinischen Fakultät Mannheim der Universität Heidelberg
 Klinikum MA Bestellen/Vormerken für Benutzer des Klinikums Mannheim
Eigene Kennung erforderlich
Bibliothek/Idn:UW / m4268382259
Lokale URL Inst.: Zum Volltext

Permanenter Link auf diesen Titel (bookmarkfähig):  https://katalog.ub.uni-heidelberg.de/titel/69038703   QR-Code

zum Seitenanfang