Papers
Topics
Authors
Recent
Search
2000 character limit reached

Depending on yourself when you should: Mentoring LLM with RL agents to become the master in cybersecurity games

Published 26 Mar 2024 in cs.CR, cs.AI, and cs.MA | (2403.17674v1)

Abstract: Integrating LLM and reinforcement learning (RL) agent effectively to achieve complementary performance is critical in high stake tasks like cybersecurity operations. In this study, we introduce SecurityBot, a LLM agent mentored by pre-trained RL agents, to support cybersecurity operations. In particularly, the LLM agent is supported with a profile module to generated behavior guidelines, a memory module to accumulate local experiences, a reflection module to re-evaluate choices, and an action module to reduce action space. Additionally, it adopts the collaboration mechanism to take suggestions from pre-trained RL agents, including a cursor for dynamic suggestion taken, an aggregator for multiple mentors' suggestions ranking and a caller for proactive suggestion asking. Building on the CybORG experiment framework, our experiences show that SecurityBot demonstrates significant performance improvement compared with LLM or RL standalone, achieving the complementary performance in the cybersecurity games.

Authors (3)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (47)
  1. Huntgpt: Integrating machine learning-based anomaly detection and explainable ai with large language models (llms). arXiv preprint arXiv:2309.16021, 2023.
  2. Marcus Botacin. Gpthreats-3: Is automatic malware generation a threat? In 2023 IEEE Security and Privacy Workshops (SPW), pages 238–254. IEEE, 2023.
  3. Do as i can, not as i say: Grounding language in robotic affordances. In Conference on Robot Learning, pages 287–318. PMLR, 2023.
  4. Eager: Asking and answering questions for automatic reward shaping in language-guided rl. Advances in Neural Information Processing Systems, 35:12478–12490, 2022.
  5. Can llm-generated misinformation be detected? arXiv preprint arXiv:2309.13788, 2023.
  6. Collaborating with language models for embodied reasoning. arXiv preprint arXiv:2302.00763, 2023.
  7. Pentestgpt: An llm-empowered automatic penetration testing tool. arXiv preprint arXiv:2308.06782, 2023.
  8. Self-collaboration code generation via chatgpt. arXiv preprint arXiv:2304.07590, 2023.
  9. Guiding pretraining in reinforcement learning with large language models. arXiv preprint arXiv:2302.06692, 2023.
  10. Polra Victor Falade. Decoding the threat landscape: Chatgpt, fraudgpt, and wormgpt in social engineering attacks. arXiv preprint arXiv:2310.05595, 2023.
  11. Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.00352, 2023.
  12. Enabling intelligent interactions between an agent and an llm: A reinforcement learning approach. arXiv preprint arXiv:2306.03604, 2023.
  13. The secret life of software vulnerabilities: A large-scale empirical study. IEEE Transactions on Software Engineering, 49(1):44–63, 2022.
  14. Survey of hallucination in natural language generation. ACM Computing Surveys, 55(12):1–38, 2023.
  15. Daniel Kahneman. Thinking, fast and slow. macmillan, 2011.
  16. Reward design with language models. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023.
  17. Camel: Communicative agents for ”mind” exploration of large language model society. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  18. Swiftsage: A generative agent with fast and slow thinking for complex interactive tasks. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  19. Eureka: Human-level reward design via coding large language models. arXiv preprint arXiv:2310.12931, 2023.
  20. Harnessing gpt-4 for generation of cybersecurity grc policies: A focus on ransomware attack mitigation. Computers & Security, 134:103424, 2023.
  21. Transformers are sample-efficient world models. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023.
  22. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602, 2013.
  23. Asynchronous methods for deep reinforcement learning. In International conference on machine learning, pages 1928–1937. PMLR, 2016.
  24. David Noever. Can large language models find and fix vulnerable software? arXiv preprint arXiv:2308.10345, 2023.
  25. Deep reinforcement learning for autonomous cyber operations: A survey, 2023.
  26. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, pages 1–22, 2023.
  27. Examining zero-shot vulnerability repair with large language models. In 2023 IEEE Symposium on Security and Privacy (SP), pages 2339–2356. IEEE, 2023.
  28. Loggpt: Exploring chatgpt for log-based anomaly detection. arXiv preprint arXiv:2309.01189, 2023.
  29. Communicative agents for software development. arXiv preprint arXiv:2307.07924, 2023.
  30. Lost at c: A user study on the security implications of large language model code assistants. arXiv preprint arXiv:2208.09727, 2023.
  31. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347, 2017.
  32. Cyborg: A gym for the development of autonomous cyber agents. arXiv preprint arXiv:2108.09118, 2021.
  33. Trusting artificial intelligence in cybersecurity is a double-edged sword. Nature Machine Intelligence, 1(12):557–560, 2019.
  34. Multi-agent collaboration: Harnessing the power of intelligent llm agents. arXiv preprint arXiv:2306.03314, 2023.
  35. Microsoft Defender Research Team. Cyberbattlesim. https://github.com/microsoft/cyberbattlesim, 2021. Created by Christian Seifert, Michael Betser, William Blum, James Bono, Kate Farris, Emily Goren, Justin Grana, Kristian Holsheimer, Brandon Marken, Joshua Neil, Nicole Nichols, Jugal Parikh, Haoran Wei.
  36. Automated cyber defence: A review, 2023.
  37. Retroformer: Pushing the limits of end-to-end retrosynthesis transformer. In International Conference on Machine Learning, pages 22475–22490. PMLR, 2022.
  38. A survey on large language model based autonomous agents. arXiv preprint arXiv:2308.11432, 2023.
  39. Humanoid agents: Platform for simulating human-like generative agents. arXiv preprint arXiv:2310.05418, 2023.
  40. Jarvis-1: Open-world multi-task agents with memory-augmented multimodal language models. arXiv preprint arXiv:2311.05997, 2023.
  41. Dual processes in reasoning? Cognition, 3(2):141–154, 1974.
  42. Autogen: Enabling next-gen llm applications via multi-agent conversation framework. arXiv preprint arXiv:2308.08155, 2023.
  43. Universal fuzzing via large language models. arXiv preprint arXiv:2308.04748, 2023.
  44. Exploring large language models for communication games: An empirical study on werewolf. arXiv preprint arXiv:2309.04658, 2023.
  45. Ferhat Yaman. Agent SCA: Advanced Physical Side Channel Analysis Agent with LLMs. PhD thesis, North Carolina State University, 2023.
  46. A survey on large language model (llm) security and privacy: The good, the bad, and the ugly. arXiv preprint arXiv:2312.02003, 2023.
  47. Exploring collaboration mechanisms for llm agents: A social psychology view. arXiv preprint arXiv:2310.02124, 2023.
Citations (4)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.

Sign Up for Free