Reinforcement Learning for Automated Cybersecurity Penetration Testing
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916825473744896 |
|---|---|
| author | López-Montero, Daniel Álvarez-Aldana, José L. Morales-Martínez, Alicia Gil-López, Marta García, Juan M. Auñón |
| author_facet | López-Montero, Daniel Álvarez-Aldana, José L. Morales-Martínez, Alicia Gil-López, Marta García, Juan M. Auñón |
| contents | This paper aims to provide an innovative machine learning-based solution to automate security testing tasks for web applications, ensuring the correct functioning of all components while reducing project maintenance costs. Reinforcement Learning is proposed to select and prioritize tools and optimize the testing path. The presented approach utilizes a simulated webpage along with its network topology to train the agent. Additionally, the model leverages Geometric Deep Learning to create priors that reduce the search space and improve learning convergence. The validation and testing process was conducted on real-world vulnerable web pages commonly used by human hackers for learning. As a result of this study, a reinforcement learning algorithm was developed that maximizes the number of vulnerabilities found while minimizing the number of steps required |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_02969 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reinforcement Learning for Automated Cybersecurity Penetration Testing López-Montero, Daniel Álvarez-Aldana, José L. Morales-Martínez, Alicia Gil-López, Marta García, Juan M. Auñón Cryptography and Security Artificial Intelligence This paper aims to provide an innovative machine learning-based solution to automate security testing tasks for web applications, ensuring the correct functioning of all components while reducing project maintenance costs. Reinforcement Learning is proposed to select and prioritize tools and optimize the testing path. The presented approach utilizes a simulated webpage along with its network topology to train the agent. Additionally, the model leverages Geometric Deep Learning to create priors that reduce the search space and improve learning convergence. The validation and testing process was conducted on real-world vulnerable web pages commonly used by human hackers for learning. As a result of this study, a reinforcement learning algorithm was developed that maximizes the number of vulnerabilities found while minimizing the number of steps required |
| title | Reinforcement Learning for Automated Cybersecurity Penetration Testing |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2507.02969 |