Proactive Cybersecurity Defense: Adaptive Threat Intelligence with Deep Reinforcement Learning

Authors

  • Prasanthi Vallurupalli  Independent Researcher, USA

Keywords:

Cybersecurity, Threat Intelligence, Deep Reinforcement Learning, Proactive Defense, Machine Learning

Abstract

As complexity increases and the threats become more frequent, it is high time for cybersecurity approaches to shift from reactive to proactive. The threat detection systems borrowed from traditional security models do not fare well against modern and intelligent attackers as these models fail to adapt to new onslaughts. Thus, our proposed adaptive threat intelligence is powered by Deep Reinforcement Learning (DRL) to improve proactive cybersecurity defense solutions presented in this paper. In DRL, machines automatically train to select every move to handle new threats in complex operating conditions. The model integrates threat feeds, anomaly detection techniques, and policy optimization approaches to decipher future cyber threats before deployment. It uses deep neural networks in combination with reinforcement learning algorithms to adapt defense approaches based on the pattern analysis of security and changes in operational conditions. Through experimental results, the better performance of DRL-driven cybersecurity technology for attack response, better detection performance, and more effective system resilience are observed. The study illustrates how AI-based adaptive security techniques help enhance infrastructure security against modern-day cyber threats.

References

  1. Khan, T., Alam, M., Akhunzada, A., Hur, A., Asif, M., & Khan, M. K. (2019). Towards augmented proactive cyberthreat intelligence. Journal of Parallel and Distributed Computing, 124, 47-59.
  2. IBRAHIM, A. (2019). AI Armory: Empowering Cybersecurity Through Machine Learning. https://www.researchgate.net/profile/Ibra-Him-5/publication/380530061_AI_Armory_Empowering_Cybersecurity_Through_Machine_Learning_AUTHORS_IBRAHIM_A/links/66410cbb35243041539fbc22/AI-Armory-Empowering-Cybersecurity-Through-Machine-Learning-AUTHORS-IBRAHIM-A.pdf
  3. IBRAHIM, A. (2019). The Cyber Frontier: AI and ML in Next-Gen Threat Detection. https://www.researchgate.net/profile/Ibra-Him-5/publication/380530011_The_Cyber_Frontier_AI_and_ML_in_Next-Gen_Threat_Detection_AUTHORS_IBRAHIM_A/links/66410b1a08aa54017a0538be/The-Cyber-Frontier-AI-and-ML-in-Next-Gen-Threat-Detection-AUTHORS-IBRAHIM-A.pdf
  4. Conti, M., Dargahi, T., & Dehghantanha, A. (2018). Cyber threat intelligence: challenges and opportunities (pp. 1-6). Springer International Publishing. https://arxiv.org/pdf/1808.01162
  5. Ayyadapu, A. K. R. (2019). A COMPREHENSIVE FRAMEWORK FOR AI-BASED THREAT INTELLIGENCE IN CLOUD CYBER SECURITY. JOURNAL OF BASIC SCIENCE AND ENGINEERING, 16(1). https://www.researchgate.net/profile/Anjan-Kumar-Ayyadapu/publication/382560466_A_COMPREHENSIVE_FRAMEWORK_FOR_AI-BASED_THREAT_INTELLIGENCE_IN_CLOUD_CYBER_SECURITY/links/66a3139bde060e4c7e5aadad/A-COMPREHENSIVE-FRAMEWORK-FOR-AI-BASED-THREAT-INTELLIGENCE-IN-CLOUD-CYBER-SECURITY.pdf
  6. Poulou, M. (2019). Information Security Event Management (SIEM) and Machine Learning Technology for Effective Intrusion Detection and Cybersecurity Threat Prevention.
  7. Zenebe, A., Shumba, M., Carillo, A., & Cuenca, S. (2019). Cyber threat discovery from dark web. EPiC Series in Computing, 64, 174-183. https://easychair.org/publications/download/MK31
  8. Sukender Reddy Mallreddy(2020).Cloud Data Security: Identifying Challenges and Implementing Solutions.JournalforEducators,TeachersandTrainers,Vol.11(1).96 -102.

Downloads

Published

2021-01-07

Issue

Section

Research Articles

How to Cite

[1]
Prasanthi Vallurupalli "Proactive Cybersecurity Defense: Adaptive Threat Intelligence with Deep Reinforcement Learning" International Journal of Scientific Research in Science and Technology(IJSRST), Online ISSN : 2395-602X, Print ISSN : 2395-6011,Volume 8, Issue 1, pp.337-342, January-February-2021.