Paper Key : IRJ************265
Author: Naga Satya Kiranmayee Sattiraju
Date Published: 07 Apr 2025
Abstract
Zero-day threats represent a significant challenge in modern cybersecurity, as they exploit previously unknown vulnerabilities before a patch is available. These attacks are particularly dangerous because they bypass traditional security mechanisms, leaving organizations exposed to critical data breaches and system compromises. The need for advanced automated systems to defend against such threats has become increasingly urgent as cybercriminals grow more sophisticated in their tactics. This paper explores the various types of cyber threats, focusing on zero-day vulnerabilities, and examines how automated systems, particularly those employing machine learning (ML) algorithms, can be deployed to detect and mitigate these risks. We will investigate the most common cyber threats, including phishing, insider threats, session hijacking, spyware, ransomware, cross-site scripting (XSS), and denial of service (DoS) attacks. Each of these threats has its unique dangers and requires a tailored defense strategy. This research delves into the techniques used to detect and defend against these threats, with a particular emphasis on automated systems and the role of ML in enhancing security measures. Through the examination of case studies and code execution examples, this paper demonstrates the real-world application of automated systems in combating zero-day and other threats. Finally, we explore the future scope of cybersecurity solutions, emphasizing the evolving role of AI and machine learning in enhancing threat detection and response capabilities.
DOI Requested