Answers are grounded in this paper and cite their sources.
with the rise of cloud computing technology there are tremendous growth on web hosting over Cloud Infrastructure. Organizations are adopting this technology and migrating from traditional client server based architecture to cloud enabled data centres. APPSEC security reports published every month shows that because of vulnerabilities in application software as hosted on cloud most of the applications are vulnerable to cyber-attacks. Attackers exploit web vulnerabilities through online attack vectors by injecting malicious payloads on HTTP/HTTPS request URLs. Successful execution of such attack vectors can compromise data Integrity, confidentiality availability by interruption, interception, fabrication and modification. The present paper proposes an advance WAF based on machine learning classification algorithms for mitigating online attack vectors. The novel approach of proposed WAF classifier is that it works as Security as a Service (SeaaS) for mitigating online attack vectors and can be used as pay as per usage policy. HTTP/HTTPS requests automatically routed to propose classifier for analysing OWASP Top 10 exploits as a first line of defence. Proposed classifier successfully blocks malicious requests and forwards legitimate requests to web server for processing. Proposed classifier is trained and tested using machine learning classification algorithms on OWASP Top 10 exploits and the accuracy is calculated based on true positive, false positive, true negative and false negative observations. Experimental results show that the proposed classifier has 98% of accuracy which is measured through key performance metrics like accuracy precision, recall, and F1 score.
No takes yet. Share an insight, caveat, or question.
Bisht et al. (2023) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: