ADAPTIVE CYBER DEFENCE FOR WEB APPLICATIONS USING BLOCKCHAIN AND ADVERSARIAL LEARNING TECHNIQUES
DOI:
https://doi.org/10.62643/Keywords:
Adaptive Cyber Defense, Web Application Security, Blockchain Technology, AdversarialAbstract
The increasing reliance on web applications for digital services has significantly expanded the attack
surface for cyber threats, making web security a critical concern for organizations. Traditional
cybersecurity mechanisms often struggle to respond effectively to evolving and sophisticated cyberattacks
such as distributed denial-of-service (DDoS), SQL injection, cross-site scripting (XSS), and automated
bot attacks. To address these challenges, adaptive cyber defense systems that incorporate advanced
technologies are required. This study proposes an adaptive cyber defense framework for web applications
that integrates blockchain technology with adversarial learning techniques to enhance security,
transparency, and resilience against cyber threats. Blockchain provides a decentralized and tamperresistant
platform for securely recording security events, maintaining audit trails, and ensuring data
integrity within the defense system. At the same time, adversarial learning techniques are employed to
train machine learning models capable of detecting malicious activities and adapting to evolving attack
patterns. The proposed system continuously monitors web traffic, analyzes behavioral patterns, and
identifies suspicious activities using adversarially trained models that improve detection accuracy and
robustness against evasion attacks. By combining the decentralized trust model of blockchain with the
adaptive capabilities of adversarial machine learning, the framework enhances the ability of web
applications to detect, respond to, and mitigate cyber threats in real time. The proposed approach aims to
create a secure, intelligent, and scalable cyber defense system capable of protecting modern web
applications from increasingly complex cyberattacks
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.













