Review on STROT: An Intelligent, Automated Red Teaming Framework using Deep Q-Learning

Year : 2025 | Volume : 12 | Issue : 03 | Page : 01 07
    By

    Pratik Suhas Pawar`,

  • Shubham Pandurang Sakhare,

  • Vishnu Latish Nair,

  • Vishal G. Puranik,

  1. Student, Department of Technology, Savitribai Phule Pune University, Pune, Maharashtra, India
  2. Student, Department of Technology, Savitribai Phule Pune University, Pune, Maharashtra, India
  3. Assistant Professor, School of Electronics and Telecommunication Engineering, Savitribai Phule Pune University, Pune, Maharashtra, India
  4. Assistant Professor, School of Electronics and Telecommunication Engineering, Savitribai Phule Pune University, Pune, Maharashtra, India

Abstract

This review examines STROT, an intelligent and automated red teaming framework designed to enhance penetration testing through the integration of machine learning and system automation. Unlike traditional approaches that require manual coordination between reconnaissance, vulnerability assessment, and exploit execution, STROT unifies these processes within a single architecture composed of a network analyzer, an AI-driven intelligence module, and an autonomous attack engine. At its core, STROT employs Deep Q-Learning to dynamically select optimal exploits based on real-time analysis, allowing the system to adapt its strategies over time. Evaluated in controlled environments, STROT demonstrated improved efficiency, reduced detection risk, and faster privilege escalation compared to conventional tools. This review highlights the framework’s strengths in automation, adaptability, and stealth while also discussing its current limitations and future potential for broader cybersecurity applications.

Keywords: Cybersecurity, red teaming, penetration testing, deep Q-learning, exploit automation, network reconnaissance, artificial intelligence, vulnerability assessment, stealth attacks, cyberattack simulation

[This article belongs to Journal of Operating Systems Development & Trends ]

How to cite this article:
Pratik Suhas Pawar`, Shubham Pandurang Sakhare, Vishnu Latish Nair, Vishal G. Puranik. Review on STROT: An Intelligent, Automated Red Teaming Framework using Deep Q-Learning. Journal of Operating Systems Development & Trends. 2025; 12(03):01-07.
How to cite this URL:
Pratik Suhas Pawar`, Shubham Pandurang Sakhare, Vishnu Latish Nair, Vishal G. Puranik. Review on STROT: An Intelligent, Automated Red Teaming Framework using Deep Q-Learning. Journal of Operating Systems Development & Trends. 2025; 12(03):01-07. Available from: https://journals.stmjournals.com/joosdt/article=2025/view=232682


References

  1. Pawar PS, Sakhare SP, Nair VL, Puranik VG. STROT: stealthy tool for root oriented tunneling – a red teaming tool. Int Res J Eng Technol. 2025 Apr; 12(4): 1–10.
  2. Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G, Petersen S. Human-level control through deep reinforcement learning. Nature. 2015 Feb; 518(7540): 529–33.
  3. Mo K, Ye P, Ren X, Wang S, Li W, Li J. Security and privacy issues in deep reinforcement learning: Threats and countermeasures. ACM Comput Surv. 2024 Feb 23; 56(6): 1–39.
  4. Chen Y, Li Y, Lu Y, Pan Z, Ji YC, Chen Y, Li Y, Shen Y. Understanding the security risks of websites using cloud storage for direct user file uploads. IEEE Trans Inf Forensics Secur. 2025 Feb 20; 20: 2677–2692.
  5. Lyon GF. (2009 Jan 1). Nmap network scanning: The official Nmap project guide to network discovery and security scanning. [Online]. Insecure.
  6. Kennedy D, O’gorman J, Kearns D, Aharoni M. Metasploit: the penetration tester’s guide. No starch press; 2011 Jul 15.
  7. Geer D, Harthorne J. Penetration testing: a duet. 18th Annual Computer Security Applications Conference, 2002. Proceedings., Las Vegas, NV, USA, 2002. p. 185-95. doi:10.1109/CSAC.2002.1176290.
  8. Applebaum A, Miller D, Strom B, Korban C, Wolf R. Intelligent, automated red team emulation. In Proceedings of the 32nd annual conference on computer security applications. 2016 Dec 5; 363–373.
  9. Zennaro FM, Erdődi L. Modelling penetration testing with reinforcement learning using capture‐the‐flag challenges: Trade‐offs between model‐free learning and a priori knowledge. IET Inf Secur. 2023 May; 17(3): 441–57.
  10. MITRE. (2025). MITRE ATT&CK. [Online]. Available from: https://www.mitre.org/focus-areas/cybersecurity/mitre-attack
Regular Issue Subscription Review Article
Volume 12
Issue 03
Received 03/10/2025
Accepted 25/10/2025
Published 19/11/2025
Publication Time 47 Days
49

Login


My IP

PlumX Metrics