AI-Powered USB Virus Alert System for Enhanced Cybersecurity

Abstract

The USB Virus Alert System signifies a progressive innovation in the domain of cybersecurity, meticulously crafted to shield computing environments from threats introduced via Universal Serial Bus (USB) devices. In today's interconnected digital landscape, USB storage media are widely utilized for rapid and convenient data exchange. However, their ubiquity has simultaneously rendered them prime vectors for malware dissemination, contributing to a surge in security vulnerabilities. Despite the presence of traditional antivirus programs, these tools predominantly rely on signature-based detection mechanisms, which are inherently limited when confronting zero-day attacks and newly emerging malicious code. Consequently, there exists a critical need for a more dynamic, adaptive solution that can effectively address both known and unknown threats in real time. This project addresses that need by engineering an advanced USB monitoring and threat detection system that functions proactively rather than reactively. At the heart of the system lies integration with the VirusTotal API, which facilitates the identification of recognized malware through signature comparison with an expansive global database. While this ensures strong protection against documented threats, the system goes further by embedding machine learning (ML) algorithms capable of conducting behavioral analysis. By monitoring deviations from normal file or device activity patterns, the system can flag potentially malicious actions, including those linked to previously unidentified malware strains. This hybrid detection model significantly enhances its efficacy, bridging the gap between conventional threat databases and adaptive anomaly detection. Furthermore, the USB Virus Alert System features a user-friendly Graphical User Interface (GUI) that simplifies interaction, thereby extending usability to individuals with minimal technical expertise. The GUI provides real-time alerts, threat logs, and system responses in a visually intuitive format. To maximize accessibility and deployment versatility, the solution is designed to be cross-platform compatible, with full functionality across Windows, Linux, and macOS operating systems. By fusing signature-based malware detection with artificial intelligence-driven behavioral analytics, this system represents a paradigm shift toward proactive cybersecurity defense. Its real-time operational capability ensures threats are detected and mitigated as they occur, reducing the window of vulnerability and minimizing potential damage. In essence, the USB Virus Alert System not only fortifies the security posture of end-user devices but also introduces a scalable, intelligent framework for managing USB-based threats, setting a precedent for future cybersecurity tools aimed at endpoint protection.

Country : Sultanate of Oman

1 Abdul Aziz Abdullah Ali Al-Musalamy2 Al-Yamama Salim Khalfan Al-Habsi3 Dr. Vimal Kumar Stephen

  1. University of Technology and Applied Sciences, Ibra, Sultanate of Oman
  2. University of Technology and Applied Sciences, Ibra, Sultanate of Oman
  3. University of Technology and Applied Sciences, Ibra, Sultanate of Oman

IRJIET, Volume 9, Issue 5, May 2025 pp. 278-283

doi.org/10.47001/IRJIET/2025.905037

References

  1. CrowdStrike. (2023). Real-time threat detection with behavioral analysis. Retrieved from https://www.crowdstrike.com
  2. Kaggle. (2023). Public malware dataset for cybersecurity research. Retrieved from https://www.kaggle.com
  3. Kaspersky Lab. (2022). USB threats in corporate environments. Retrieved from https://www.kaspersky.com
  4. Khan, A., et al. (2020). Deep learning for USB malware detection. International Journal of Computer Science, 15(2), 123–135.
  5. McAfee. (2023). Automated malware quarantine and reporting. Retrieved from https://www.mcafee.com
  6. McAfee Endpoint Security. (2022). Automatic quarantine and user notification features. Retrieved from https://www.mcafee.com
  7. Moskovitch, R., et al. (2008). Malware detection via behavioral analysis. Journal of Cybersecurity, 12(3), 45–60.
  8. Palanisamy, R., & Mathivanan, V. (2017). Performance metrics analysis for simulation protocols. Journal of Advanced Research in Dynamical and Control Systems (JARDCS), 18(Special Issue), 2449–2462.
  9. Palanisamy, R., & Mathivanan, V. (2019). Future algorithm for optimised path selection and detection in MANET. International Journal of Networking and Virtual Organisations, 21(2).
  10. Palo Alto Networks. (2021). Network traffic monitoring for malware detection. Retrieved from https://www.paloaltonetworks.com
  11. Palo Alto Networks. (2023). Network monitoring for USB malware detection. Retrieved from https://www.paloaltonetworks.com
  12. Python Software Foundation. (n.d.-a). Python psutil library documentation. Retrieved from https://psrutil.readthedocs.io/
  13. Python Software Foundation. (n.d.-b). Python smtplib library documentation. Retrieved from https://docs.python.org/3/library/smtplib.html
  14. Scikit-learn Developers. (n.d.). Scikit-learn: Machine learning in Python. Retrieved from https://scikit-learn.org/
  15. Scikit-learn. (2023). Machine learning for cybersecurity. Retrieved from https://scikit-learn.org
  16. Shabtai, R., Moskovitch, Y., Elovici, C., & Glezer, C. (2014). Machine learning for malware detection. In Machine Learning and Data Mining in Pattern Recognition (pp. 1–12). Springer, Berlin, Heidelberg.
  17. Smith, J. (2020). Cross-platform development: Tools and techniques. Journal of Software Engineering, 15(3), 45–60.
  18. Symantec. (2023). Internet security threat report. Retrieved from https://www.symantec.com
  19. Symantec. (2023). USB device threat analysis. Retrieved from https://www.symantec.com
  20. TensorFlow Developers. (n.d.). TensorFlow: An end-to-end open-source platform for machine learning. Retrieved from https://www.tensorflow.org/
  21. TensorFlow. (2023). Deep learning for threat detection. Retrieved from https://www.tensorflow.org
  22. VirusTotal API Documentation. (n.d.). Retrieved from https://developers.virustotal.com/
  23. VirusTotal. (2023). Malware detection and threat intelligence reports. Retrieved from https://www.virustotal.com/