Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.06539 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914234693058560 |
|---|---|
| author | Le, Duc Huy Stadler, Rolf |
| author_facet | Le, Duc Huy Stadler, Rolf |
| contents | CAGE-2 is an accepted benchmark for learning and evaluating defender strategies against cyberattacks. It reflects a scenario where a defender agent protects an IT infrastructure against various attacks. Many defender methods for CAGE-2 have been proposed in the literature. In this paper, we construct a formal model for CAGE-2 using the framework of Partially Observable Markov Decision Process (POMDP). Based on this model, we define an optimal defender strategy for CAGE-2 and introduce a method to efficiently learn this strategy. Our method, called BF-PPO, is based on PPO, and it uses particle filter to mitigate the computational complexity due to the large state space of the CAGE-2 model. We evaluate our method in the CAGE-2 CybORG environment and compare its performance with that of CARDIFF, the highest ranked method on the CAGE-2 leaderboard. We find that our method outperforms CARDIFF regarding the learned defender strategy and the required training time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_06539 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Optimal Defender Strategies for CAGE-2 using a POMDP Model Le, Duc Huy Stadler, Rolf Machine Learning Artificial Intelligence CAGE-2 is an accepted benchmark for learning and evaluating defender strategies against cyberattacks. It reflects a scenario where a defender agent protects an IT infrastructure against various attacks. Many defender methods for CAGE-2 have been proposed in the literature. In this paper, we construct a formal model for CAGE-2 using the framework of Partially Observable Markov Decision Process (POMDP). Based on this model, we define an optimal defender strategy for CAGE-2 and introduce a method to efficiently learn this strategy. Our method, called BF-PPO, is based on PPO, and it uses particle filter to mitigate the computational complexity due to the large state space of the CAGE-2 model. We evaluate our method in the CAGE-2 CybORG environment and compare its performance with that of CARDIFF, the highest ranked method on the CAGE-2 leaderboard. We find that our method outperforms CARDIFF regarding the learned defender strategy and the required training time. |
| title | Learning Optimal Defender Strategies for CAGE-2 using a POMDP Model |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2509.06539 |