Blick ins Buch

Machine Learning under Malware Attack

Raphael Labaca-Castro (Autor)

Buch | Softcover

XXXIV, 116 Seiten

2023 | 1st ed. 2023
Springer Fachmedien Wiesbaden GmbH (Verlag)
978-3-658-40441-3 (ISBN)

Lese- und Medienproben

Inhaltsverzeichnis (PDF)

Artikel merken

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.

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.

The Beginnings of Adversarial ML.- Framework for Adversarial Malware Evaluation.- Problem-Space Attacks.- Feature-Space Attacks.- Closing Remarks.

Erscheinungsdatum	03.02.2023
Zusatzinfo	XXXIV, 116 p. 19 illus., 11 illus. in color. Textbook for German language market.
Verlagsort	Wiesbaden
Sprache	englisch
Maße	148 x 210 mm
Gewicht	209 g
Themenwelt	Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik
Themenwelt	Technik ► Fahrzeugbau / Schiffbau
Schlagworte	Adversarial ML • Computer Security • Fame • machine learning • Malware • trustworthy AI
ISBN-10	3-658-40441-8 / 3658404418
ISBN-13	978-3-658-40441-3 / 9783658404413
Zustand	Neuware