A Red Teaming Framework for Securing AI in Maritime Autonomous Systems
Artificial intelligence (AI) is being ubiquitously adopted to automate processes in science and industry. However, due to its often intricate and opaque nature, AI has been shown to possess inherent vulnerabilities which can be maliciously exploited with adversarial AI, potentially putting AI users...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | Applied Artificial Intelligence |
| Online Access: | https://www.tandfonline.com/doi/10.1080/08839514.2024.2395750 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846119945527623680 |
|---|---|
| author | Mathew J. Walter Aaron Barrett Kimberly Tam |
| author_facet | Mathew J. Walter Aaron Barrett Kimberly Tam |
| author_sort | Mathew J. Walter |
| collection | DOAJ |
| description | Artificial intelligence (AI) is being ubiquitously adopted to automate processes in science and industry. However, due to its often intricate and opaque nature, AI has been shown to possess inherent vulnerabilities which can be maliciously exploited with adversarial AI, potentially putting AI users and developers at both cyber and physical risk. In addition, there is insufficient comprehension of the real-world effects of adversarial AI and an inadequacy of AI security examinations; therefore, the growing threat landscape is unknown for many AI solutions. To mitigate this issue, we propose one of the first red team frameworks for evaluating the AI security of maritime autonomous systems. The framework provides operators with a proactive (secure by design) and reactive (post-deployment evaluation) response to securing AI technology today and in the future. This framework is a multi-part checklist, which can be tailored to different systems and requirements. We demonstrate this framework to be highly effective for a red team to use to uncover numerous vulnerabilities within a real-world maritime autonomous systems AI, ranging from poisoning to adversarial patch attacks. The lessons learned from systematic AI red teaming can help prevent MAS-related catastrophic events in a world with increasing uptake and reliance on mission-critical AI. |
| format | Article |
| id | doaj-art-b9519f6c08ab4ec88c5e260c8231f4ab |
| institution | Kabale University |
| issn | 0883-9514 1087-6545 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Applied Artificial Intelligence |
| spelling | doaj-art-b9519f6c08ab4ec88c5e260c8231f4ab2024-12-16T16:13:01ZengTaylor & Francis GroupApplied Artificial Intelligence0883-95141087-65452024-12-0138110.1080/08839514.2024.2395750A Red Teaming Framework for Securing AI in Maritime Autonomous SystemsMathew J. Walter0Aaron Barrett1Kimberly Tam2School of Engineering, Computing and Mathematics, University of Plymouth, Plymouth, UKSchool of Engineering, Computing and Mathematics, University of Plymouth, Plymouth, UKSchool of Engineering, Computing and Mathematics, University of Plymouth, Plymouth, UKArtificial intelligence (AI) is being ubiquitously adopted to automate processes in science and industry. However, due to its often intricate and opaque nature, AI has been shown to possess inherent vulnerabilities which can be maliciously exploited with adversarial AI, potentially putting AI users and developers at both cyber and physical risk. In addition, there is insufficient comprehension of the real-world effects of adversarial AI and an inadequacy of AI security examinations; therefore, the growing threat landscape is unknown for many AI solutions. To mitigate this issue, we propose one of the first red team frameworks for evaluating the AI security of maritime autonomous systems. The framework provides operators with a proactive (secure by design) and reactive (post-deployment evaluation) response to securing AI technology today and in the future. This framework is a multi-part checklist, which can be tailored to different systems and requirements. We demonstrate this framework to be highly effective for a red team to use to uncover numerous vulnerabilities within a real-world maritime autonomous systems AI, ranging from poisoning to adversarial patch attacks. The lessons learned from systematic AI red teaming can help prevent MAS-related catastrophic events in a world with increasing uptake and reliance on mission-critical AI.https://www.tandfonline.com/doi/10.1080/08839514.2024.2395750 |
| spellingShingle | Mathew J. Walter Aaron Barrett Kimberly Tam A Red Teaming Framework for Securing AI in Maritime Autonomous Systems Applied Artificial Intelligence |
| title | A Red Teaming Framework for Securing AI in Maritime Autonomous Systems |
| title_full | A Red Teaming Framework for Securing AI in Maritime Autonomous Systems |
| title_fullStr | A Red Teaming Framework for Securing AI in Maritime Autonomous Systems |
| title_full_unstemmed | A Red Teaming Framework for Securing AI in Maritime Autonomous Systems |
| title_short | A Red Teaming Framework for Securing AI in Maritime Autonomous Systems |
| title_sort | red teaming framework for securing ai in maritime autonomous systems |
| url | https://www.tandfonline.com/doi/10.1080/08839514.2024.2395750 |
| work_keys_str_mv | AT mathewjwalter aredteamingframeworkforsecuringaiinmaritimeautonomoussystems AT aaronbarrett aredteamingframeworkforsecuringaiinmaritimeautonomoussystems AT kimberlytam aredteamingframeworkforsecuringaiinmaritimeautonomoussystems AT mathewjwalter redteamingframeworkforsecuringaiinmaritimeautonomoussystems AT aaronbarrett redteamingframeworkforsecuringaiinmaritimeautonomoussystems AT kimberlytam redteamingframeworkforsecuringaiinmaritimeautonomoussystems |