Nicola De Siati
Deep Learning for Anomaly Detection in Cybersecurity: Methods and Performance Evaluation.
Rel. Massimo Violante. Politecnico di Torino, Corso di laurea magistrale in Mechatronic Engineering (Ingegneria Meccatronica), 2025
Abstract
Cybersecurity is essential in today's digital world, where connected devices are prevalent, and large volumes of sensitive data transfer are common. This growing dependency exposes both organizations and individuals to increasingly sophisticated attacks that traditional security solutions fail to mitigate. Traditional methods that rely on rule-based or signature-based approaches are unable to keep up with the pace of these emerging threats. The evolution of cyberattacks shows how resilient malicious actors can be. Older attacks were comparatively straightforward to today’s threats. Modern cyberattacks employ advanced persistent threats, polymorphic malware, and social engineering techniques. They frequently take advantage of zero-day vulnerabilities—security holes known to no one who sells software and without any patch—so that defences that would ordinarily stop them do not.
The tendency of new malware or attack techniques to drift from established patterns makes them difficult—even impossible—to spot, which offers opportunities to prey on systems
Relatori
Anno Accademico
Tipo di pubblicazione
Numero di pagine
Informazioni aggiuntive
Corso di laurea
Classe di laurea
Aziende collaboratrici
URI
![]() |
Modifica (riservato agli operatori) |
