• Home
  • Search
  • Artificial Intelligence for Threat Detection: Leveraging Deep Learning to Identify Zero-Day Attacks in Real Time
  • https://doi.org/10.70315/uloap.ulete.2025.0204013Copy DOI Icon

Artificial Intelligence for Threat Detection: Leveraging Deep Learning to Identify Zero-Day Attacks in Real Time

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

The article examines the use of deep artificial intelligence models to detect zero-day attacks amid rapidly escalating cyber-threat complexity. The relevance stems from the fact that the emergence rate of zero-day exploits consistently outpaces the rate of signature generation. At the same time, traffic encryption, malware polymorphism, and the growth of attack automation markedly degrade the efficacy of classical IDS. The objective is to conduct a systematic analysis of deep learning’s potential to provide real-time detection of unknown vulnerabilities and to assess the architectures, training regimes, and telemetry requirements that determine a model’s ability to recognize previously unobserved patterns. The study’s novelty lies in a multi-level methodological integration: mapping modern neural architectures to the characteristics of enterprise traffic, analyzing model robustness to concept drift and adversarial interference, and evaluating prospects for autonomous vulnerability remediation and the use of post-quantum cryptographic mechanisms in distributed learning. The main findings underscore that deep learning transforms the threat-detection paradigm: it shifts defense from retrospective signatures to behavioral baselines, compresses dwell time from days to seconds, and enables a reactive-proactive security loop. The effectiveness of such systems is determined not only by architectural choice, but also by the maturity of telemetry collection, verification, and versioning processes; resilience to data poisoning; decision interpretability; and engineering optimization of computational pipelines. The work also identifies critical constraints: scarcity of labeled traces, behavioral drift, hardware costs, and the risk of model compromise. These limits delineate development directions, from generating temporary patches with large language models to offloading inference to edge devices and employing digital twins for continuous self-training of detection systems. The article will be of use to researchers, security engineers, and SOC professionals deploying behavioral mechanisms for zero-day attack detection.

Similar Papers
  • Conference Article
  • Citations62

Deep Reinforcement Learning based Smart Mitigation of DDoS Flooding in Software-Defined Networks

  • Sep 01, 2018
  • Yandong Liu +4
  • Book Chapter
  • Citations1

Network Intrusion Detection Adversarial Attacks for LEO Constellation Networks Based on Deep Learning

  • Jan 01, 2022
  • Yunhao Li +6
  • Research Article

Securing Cloud-Native Microservices Using AI-Driven Threat Detection Models

  • Dec 17, 2025
  • International Journal of Research and Review in Applied Science Humanities and Technology
  • Minati Mishra
  • Conference Article
  • Citations288

Toward an Online Anomaly Intrusion Detection System Based on Deep Learning

  • Dec 01, 2016
  • Khaled Alrawashdeh +1
  • Research Article
  • Citations3

Exploring Zero-Day Attacks on Machine Learning and Deep Learning Algorithms

  • Jun 21, 2024
  • European Conference on Cyber Warfare and Security
  • Marie Kovářová
  • Research Article
  • Citations2

Enhancing network security using unsupervised learning approach to combat zero-day attack

  • Nov 01, 2024
  • Indonesian Journal of Electrical Engineering and Computer Science
  • Rajakumar Perumal +4
  • Research Article

Enhancing phishing detection with dynamic optimization and character-level deep learning in cloud environments.

  • May 19, 2025
  • PeerJ. Computer science
  • Vishnukumar Ravula +1
  • Research Article

AI-driven cybersecurity in software engineering

  • Sep 30, 2025
  • World Journal of Advanced Research and Reviews
  • Harsh Verma
  • Research Article
  • Citations1

A NOVEL APPROACH FOR ADDRESSING IOT NETWORKS VULNERABILITIES IN DETECTION AND CLASSIFICATION OF DOS/DDOS ATTACKS

  • Oct 02, 2024
  • International Journal of Software Engineering and Computer Systems
  • Aisha Ibrahim Gide +1
  • PDF
  • Research Article
  • Citations31

Distributed Deep Reinforcement Learning: A Survey and a Multi-player Multi-agent Learning Toolbox

  • Jan 11, 2024
  • Machine Intelligence Research
  • Qiyue Yin +8
  • Conference Article
  • Citations17

EVAX: Towards a Practical, Pro-active & Adaptive Architecture for High Performance & Security

  • Oct 01, 2022
  • Samira Mirbagher Ajorpaz +5
  • Research Article

AI for Zero-Day Threat Prediction and Mitigation

  • Oct 11, 2025
  • INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT
  • Vaibhav Jotangiyai +4
  • PDF
  • Research Article
  • Citations127

Generative Deep Learning to Detect Cyberattacks for the IoT-23 Dataset

  • Jan 01, 2022
  • IEEE Access
  • N Abdalgawad +4
  • Research Article

TOWARD HYBRID DEEP LEARNING-BASED THREAT DETECTION WITH BLOCKCHAIN TECHNOLOGY FOR SECURE IOT-BASED CONSUMER ELECTRONICS

  • Nov 26, 2024
  • Fractals
  • Mesfer Al Duhayyim
  • Conference Article

A Federated Deep Learning Framework for Zero-Day Threat Detection on Edge Devices

  • Nov 06, 2025
  • Madhinapalli Dileep Kumar Reddy +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.