Key points are not available for this paper at this time.
The digital world is rapidly coming together as well as transforming a lot of our valued data onto digital forms. Its consequent dissemination eased via the advent of the Internet has also encountered many attacks due to predictable responses from many users – leading up to social engineering and exploits on trust-level of users. The use of deception is now playing a very prominent role in enhancing data security. Several approaches abound to discourage and redirect challenges (via the use of honeypot), and to detect such intrusive activities (via an intrusion detection systems). These have been successfully used to minimize security breaches. We explore a deep learning deception-based honeypot to minimize breaches by adversaries. Used on web servers, it is equipped with identification capabilities as the system learns and defends a user system against intrusive actions. Our confusion matrix shows model has sensitivity of 0.81, specificity 0.08, and prediction accuracy of 0.991 with an improvement rate of 0.39 for data that were not originally used to train. . Keywords: Web Server, HoneyPot, Integratio, Injection Approach, Malware Intrusion Detection CISDI Journal Reference Format Malasowe B., Aghware, F. & Edim, B.E. (2024): Pilot Study on Web Server HoneyPot Integration Using Injection Approach for Malware Intrusion Detection. Computing, Information Systems, Development Informatics & Allied Research Journal. Vol 15 No 1, Pp 13-.28. dx.doi.org/10.22624/AIMS/CISDI/V15N1P2. Available online at www.isteams.net/cisdijournal
Malasowe et al. (Sat,) studied this question.