Security and Artificial Intelligence

A Crossdisciplinary Approach

Lejla Batina, Thomas Bäck, Ileana Buhan, Stjepan Picek (Herausgeber)

Buch | Softcover

X, 361 Seiten

2022 | 1st ed. 2022
Springer International Publishing (Verlag)
978-3-030-98794-7 (ISBN)

Artikel merken

AI has become an emerging technology to assess security and privacy, with many challenges and potential solutions at the algorithm, architecture, and implementation levels. So far, research on AI and security has looked at subproblems in isolation but future solutions will require sharing of experience and best practice in these domains.

The editors of this State-of-the-Art Survey invited a cross-disciplinary team of researchers to a Lorentz workshop in 2019 to improve collaboration in these areas. Some contributions were initiated at the event, others were developed since through further invitations, editing, and cross-reviewing. This contributed book contains 14 invited chapters that address side-channel attacks and fault injection, cryptographic primitives, adversarial machine learning, and intrusion detection. The chapters were evaluated based on their significance, technical quality, and relevance to the topics of security and AI, and each submission was reviewed in single-blindmode and revised.

AI for Cryptography.- Artificial Intelligence for the Design of Symmetric Cryptographic Primitives.- Traditional Machine Learning Methods for Side-Channel Analysis.- Deep Learning on Side-Channel Analysis.- Artificial Neural Networks and Fault Injection Attacks.- Physically Unclonable Functions and AI: Two Decades of Marriage.- AI for Authentication and Privacy.- Privacy-Preserving Machine Learning using Cryptography.- Machine Learning Meets Data Modification: the Potential of Pre-processing for Privacy Enhancement.- AI for Biometric Authentication Systems.- Machine Learning and Deep Learning for Hardware Fingerprinting. - AI for Intrusion Detection.- Intelligent Malware Defenses.- Open-World Network Intrusion Detection.- Security of AI.- Adversarial Machine Learning.- Deep Learning Backdoors. - On Implementation-level Security of Edge-based Machine Learning Models.

Erscheinungsdatum	10.04.2022
Reihe/Serie	Lecture Notes in Computer Science
Zusatzinfo	X, 361 p. 43 illus., 28 illus. in color.
Verlagsort	Cham
Sprache	englisch
Maße	155 x 235 mm
Gewicht	569 g
Themenwelt	Informatik ► Netzwerke ► Sicherheit / Firewall
Themenwelt	Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik
Schlagworte	Adversarial Machine Learning • Applications • Artificial Intelligence • authentication • Biometric Authentication Systems • computer crime • Computer Science • conference proceedings • cryptography • Data Security • Deep Learning Backdoors • fault injection • Hardware Fingerprinting • Informatics • machine learning • Malware • Network Intrusion Detection • Network Protocols • Network Security • Physically unclonable functions • privacy • Privacy Enhancement • Privacy-Preserving Machine Learning • Research • Side-Channel Analysis
ISBN-10	3-030-98794-9 / 3030987949
ISBN-13	978-3-030-98794-7 / 9783030987947
Zustand	Neuware