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

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...

Full description

Bibliographic Details
Main Author: Bergadano, Francesco
Other Authors: Giacinto, Giorgio
Format: eBook
Language:English
Published: Basel MDPI - Multidisciplinary Digital Publishing Institute 2023
Subjects:
N/a
Ids
Online Access:
Collection: Directory of Open Access Books - Collection details see MPG.ReNa
LEADER 04500nma a2200889 u 4500
001 EB002173786
003 EBX01000000000000001311563
005 00000000000000.0
007 cr|||||||||||||||||||||
008 230811 ||| eng
020 |a 9783036582658 
020 |a 9783036582641 
020 |a books978-3-0365-8265-8 
100 1 |a Bergadano, Francesco 
245 0 0 |a AI for Cybersecurity: Robust models for Authentication, Threat and Anomaly Detection  |h Elektronische Ressource 
260 |a Basel  |b MDPI - Multidisciplinary Digital Publishing Institute  |c 2023 
300 |a 1 electronic resource (208 p.) 
653 |a biometric cryptosystem 
653 |a machine learning 
653 |a false negative rate 
653 |a performance comparison 
653 |a risk identification 
653 |a MITRE ATT&CK Matrix 
653 |a n/a 
653 |a BERT-based multi-labeling 
653 |a cooperative intelligent transportation systems (cITSs) 
653 |a deep belief network (DBN) 
653 |a attack detection 
653 |a deep learning 
653 |a iris identification 
653 |a non-targeted attack 
653 |a vulnerability 
653 |a neural networks 
653 |a tree-based ensemble 
653 |a History of engineering & technology / bicssc 
653 |a adaptive model 
653 |a NIDS 
653 |a Technology: general issues / bicssc 
653 |a vehicular ad-hoc networks (VANET) 
653 |a datasets 
653 |a cyber threats 
653 |a artificial neural network 
653 |a Internet of Things 
653 |a IDS 
653 |a targeted attack 
653 |a adversarial examples 
653 |a network traffic 
653 |a evaluation metrics 
653 |a Mechanical engineering & materials / bicssc 
653 |a smart grid 
653 |a techniques classification 
653 |a cyber-physical system 
653 |a malware detection 
653 |a face recognition 
653 |a mask matrix 
653 |a statistical significance test 
653 |a formal ontology 
653 |a anomaly detection 
653 |a cybersecurity 
653 |a portable executable malware 
653 |a intrusion detection 
653 |a error-correcting codes 
700 1 |a Giacinto, Giorgio 
700 1 |a Bergadano, Francesco 
700 1 |a Giacinto, Giorgio 
041 0 7 |a eng  |2 ISO 639-2 
989 |b DOAB  |a Directory of Open Access Books 
500 |a Creative Commons (cc), https://creativecommons.org/licenses/by/4.0/ 
024 8 |a 10.3390/books978-3-0365-8265-8 
856 4 2 |u https://directory.doabooks.org/handle/20.500.12854/112521  |z DOAB: description of the publication 
856 4 0 |u https://www.mdpi.com/books/book/7647  |x Verlag  |3 Volltext 
082 0 |a 900 
082 0 |a 380 
082 0 |a 700 
082 0 |a 600 
082 0 |a 620 
520 |a 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 multilevel authentication, complex application and network monitoring, and anomaly detection. We refer to this as the “anomaly detection continuum”. Machine learning and other artificial intelligence technologies can provide powerful tools for addressing such issues, but the robustness of the obtained models is often ignored or underestimated. On the one hand, AI-based algorithms can be replicated by malicious opponents, and attacks can be devised so that they will not be detected (evasion attacks). On the other hand, data and system contexts can be modified by attackers to influence the countermeasures obtained from machine learning and render them ineffective (active data poisoning). This Special Issue presents ten papers that can be grouped under five main topics: (1) Cyber–Physical Systems (CPSs), (2) Intrusion Detection, (3) Malware Analysis, (4) Access Control, and (5) Threat intelligence.AI is increasingly being used in cybersecurity, with three main directions of current research: (1) new areas of cybersecurity are being addressed, such as CPS security and threat intelligence; (2) more stable and consistent results are being presented, sometimes with surprising accuracy and effectiveness; and (3) the presence of an AI-aware adversary is recognized and analyzed, producing more robust solutions.