A Game Theory-Based System to Defend Against Multimedia Message Service Phishing
Open AccessSocial engineering attacks are unique from other forms of cyber intrusion because their success is based on human factors that are not easily translatable to traditional cybersecurity defense measures. By manipulating human behavior, attackers can gain access to confidential data and systems. Phishing – a prominent form of such an attack - is an exponentially increasing threat that continually evolves to lure new victims, with millions of scam e-mails, texts, voice calls, and messages being sent yearly. This research introduces a novel system to prevent successful phishing attempts in text messages for phones and other applications. The system developed incorporates game theory principles into modified Naïve Bayes and machine learning techniques. This system was tested for accuracy and speed alongside popularly ranked anti-phishing applications for Android by using a set of English-language based messages and phone numbers. The results show that the proposed system achieved accuracy of approximately 99% while the competitors had mean accuracy rates ranging from 91% to 86%. Similarly, the game theory system had mean detection response speeds of approximately 32 milliseconds while the competitors showed mean speeds ranging from 43 to 99 milliseconds. The study’s results show that the proposed game theory system has higher accuracy and speed than that of competitors showing promise in the use of game theory in training and deployment. This study can be used to create future anti-phishing models in a variety of settings.
- All rights reserved
Notice to Authors
If you are the author of this work and you have any questions about the information on this page, please use the Contact form to get in touch with us.
| Thumbnail | Title | Date Uploaded | Visibility | Actions |
|---|---|---|---|---|
|
|
Makeswaran_gwu_0075A_16657.pdf | 2024-01-11 | Open Access |
|