Towards Type Agnostic Cyber Defense Agents
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912140694126592 |
|---|---|
| author | Galinkin, Erick Pountrourakis, Emmanouil Mancoridis, Spiros |
| author_facet | Galinkin, Erick Pountrourakis, Emmanouil Mancoridis, Spiros |
| contents | With computing now ubiquitous across government, industry, and education, cybersecurity has become a critical component for every organization on the planet. Due to this ubiquity of computing, cyber threats have continued to grow year over year, leading to labor shortages and a skills gap in cybersecurity. As a result, many cybersecurity product vendors and security organizations have looked to artificial intelligence to shore up their defenses. This work considers how to characterize attackers and defenders in one approach to the automation of cyber defense -- the application of reinforcement learning. Specifically, we characterize the types of attackers and defenders in the sense of Bayesian games and, using reinforcement learning, derive empirical findings about how to best train agents that defend against multiple types of attackers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_01542 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Type Agnostic Cyber Defense Agents Galinkin, Erick Pountrourakis, Emmanouil Mancoridis, Spiros Cryptography and Security Artificial Intelligence Computer Science and Game Theory Machine Learning With computing now ubiquitous across government, industry, and education, cybersecurity has become a critical component for every organization on the planet. Due to this ubiquity of computing, cyber threats have continued to grow year over year, leading to labor shortages and a skills gap in cybersecurity. As a result, many cybersecurity product vendors and security organizations have looked to artificial intelligence to shore up their defenses. This work considers how to characterize attackers and defenders in one approach to the automation of cyber defense -- the application of reinforcement learning. Specifically, we characterize the types of attackers and defenders in the sense of Bayesian games and, using reinforcement learning, derive empirical findings about how to best train agents that defend against multiple types of attackers. |
| title | Towards Type Agnostic Cyber Defense Agents |
| topic | Cryptography and Security Artificial Intelligence Computer Science and Game Theory Machine Learning |
| url | https://arxiv.org/abs/2412.01542 |