Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2505.22531 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909648204857344 |
|---|---|
| author | Molina-Markham, Andres Robaina, Luis Steinle, Sean Trivedi, Akash Tsui, Derek Potteiger, Nicholas Brandt, Lauren Winder, Ransom Ridley, Ahmad |
| author_facet | Molina-Markham, Andres Robaina, Luis Steinle, Sean Trivedi, Akash Tsui, Derek Potteiger, Nicholas Brandt, Lauren Winder, Ransom Ridley, Ahmad |
| contents | Open-ended learning (OEL) -- which emphasizes training agents that achieve broad capability over narrow competency -- is emerging as a paradigm to develop artificial intelligence (AI) agents to achieve robustness and generalization. However, despite promising results that demonstrate the benefits of OEL, applying OEL to develop autonomous agents for real-world cybersecurity applications remains a challenge.
We propose a training approach, inspired by OEL, to develop autonomous network defenders. Our results demonstrate that like in other domains, OEL principles can translate into more robust and generalizable agents for cyber defense. To apply OEL to network defense, it is necessary to address several technical challenges. Most importantly, it is critical to provide a task representation approach over a broad universe of tasks that maintains a consistent interface over goals, rewards and action spaces. This way, the learning agent can train with varying network conditions, attacker behaviors, and defender goals while being able to build on previously gained knowledge.
With our tools and results, we aim to fundamentally impact research that applies AI to solve cybersecurity problems. Specifically, as researchers develop gyms and benchmarks for cyber defense, it is paramount that they consider diverse tasks with consistent representations, such as those we propose in our work. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_22531 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Training RL Agents for Multi-Objective Network Defense Tasks Molina-Markham, Andres Robaina, Luis Steinle, Sean Trivedi, Akash Tsui, Derek Potteiger, Nicholas Brandt, Lauren Winder, Ransom Ridley, Ahmad Machine Learning Artificial Intelligence Cryptography and Security Open-ended learning (OEL) -- which emphasizes training agents that achieve broad capability over narrow competency -- is emerging as a paradigm to develop artificial intelligence (AI) agents to achieve robustness and generalization. However, despite promising results that demonstrate the benefits of OEL, applying OEL to develop autonomous agents for real-world cybersecurity applications remains a challenge. We propose a training approach, inspired by OEL, to develop autonomous network defenders. Our results demonstrate that like in other domains, OEL principles can translate into more robust and generalizable agents for cyber defense. To apply OEL to network defense, it is necessary to address several technical challenges. Most importantly, it is critical to provide a task representation approach over a broad universe of tasks that maintains a consistent interface over goals, rewards and action spaces. This way, the learning agent can train with varying network conditions, attacker behaviors, and defender goals while being able to build on previously gained knowledge. With our tools and results, we aim to fundamentally impact research that applies AI to solve cybersecurity problems. Specifically, as researchers develop gyms and benchmarks for cyber defense, it is paramount that they consider diverse tasks with consistent representations, such as those we propose in our work. |
| title | Training RL Agents for Multi-Objective Network Defense Tasks |
| topic | Machine Learning Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2505.22531 |