AI for Cybersecurity: Robust models for Authentication, Threat and Anomaly Detection

• Andere auteurs: Bergadano, Francesco (Redacteur), Giacinto, Giorgio (Redacteur)
• Formaat: Elektronisch Hoofdstuk
• Taal: Engels
• Gepubliceerd in: Basel MDPI - Multidisciplinary Digital Publishing Institute 2023
• Onderwerpen: Technology: general issues; History of engineering & technology; Mechanical engineering & materials; Internet of Things; cybersecurity; cyber threats; malware detection; machine learning; network traffic; cooperative intelligent transportation systems (cITSs); IDS; vehicular ad-hoc networks (VANET); adaptive model; deep belief network (DBN); NIDS; deep learning; false negative rate; artificial neural network; MITRE ATT&CK Matrix; techniques classification; BERT-based multi-labeling; formal ontology; risk identification; vulnerability; portable executable malware; tree-based ensemble; performance comparison; statistical significance test; adversarial examples; face recognition; mask matrix; targeted attack; non-targeted attack; anomaly detection; attack detection; cyber-physical system; datasets; evaluation metrics; biometric cryptosystem; iris identification; error-correcting codes; intrusion detection; smart grid; neural networks; n/a
• Online toegang: DOAB: download the publication; DOAB: description of the publication

Cybersecurity models include provisions for legitimate user and agent authentication, as well as algorithms for detecting external threats, such as intruders and malicious software. In particular, we can define a continuum of cybersecurity measures ranging from user identification to risk-based and...