Towards Trustworthy AI: Analyzing Model Uncertainty through Monte Carlo Dropout and Noise Injection
Autonomous vehicles require intelligent computer vision (CV) to perform critical navigational perception tasks. To achieve this, sensors such as camera, LiDAR and radar are utilized to provide data to artificial intelligence (AI) systems. Continuous monitoring of these intelligent CV systems is req...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
LibraryPress@UF
2025-05-01
|
| Series: | Proceedings of the International Florida Artificial Intelligence Research Society Conference |
| Online Access: | https://journals.flvc.org/FLAIRS/article/view/138945 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850272206008877056 |
|---|---|
| author | Chern Chao Tai Wesam Al Amiri Abhijeet Solanki Douglas Alan Talbert Nan Guo Syed Rafay Hasan |
| author_facet | Chern Chao Tai Wesam Al Amiri Abhijeet Solanki Douglas Alan Talbert Nan Guo Syed Rafay Hasan |
| author_sort | Chern Chao Tai |
| collection | DOAJ |
| description |
Autonomous vehicles require intelligent computer vision (CV) to perform critical navigational perception tasks. To achieve this, sensors such as camera, LiDAR and radar are utilized to provide data to artificial intelligence (AI) systems. Continuous monitoring of these intelligent CV systems is required to achieve a trustworthy AI system in a zero-trust (ZT) environment. This paper introduces a novel two-stage framework that provides a mechanism towards achieving this monitoring for a ZT environment. We made use of Monte Carlo (MC) dropout with One-Class Classification techniques to propose a framework towards trustworthy AI systems for AVs. Through extensive experimentation with varying noise levels and number of MC samples, we demonstrate that our framework achieves promising results in anomaly detection. In particular, our framework explores the trade-off between detection accuracy and computational overhead, where we achieved a high FPS of 46.4 with MC size of 5 while the accuracy is as low as 61.5%. This study would provide us with valuable insights for real-world AV applications.
|
| format | Article |
| id | doaj-art-c74da8ffc1aa4f609e58caa20d770cc5 |
| institution | OA Journals |
| issn | 2334-0754 2334-0762 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | LibraryPress@UF |
| record_format | Article |
| series | Proceedings of the International Florida Artificial Intelligence Research Society Conference |
| spelling | doaj-art-c74da8ffc1aa4f609e58caa20d770cc52025-08-20T01:51:54ZengLibraryPress@UFProceedings of the International Florida Artificial Intelligence Research Society Conference2334-07542334-07622025-05-0138110.32473/flairs.38.1.138945Towards Trustworthy AI: Analyzing Model Uncertainty through Monte Carlo Dropout and Noise InjectionChern Chao Tai0Wesam Al AmiriAbhijeet SolankiDouglas Alan TalbertNan GuoSyed Rafay HasanTennessee Technological University Autonomous vehicles require intelligent computer vision (CV) to perform critical navigational perception tasks. To achieve this, sensors such as camera, LiDAR and radar are utilized to provide data to artificial intelligence (AI) systems. Continuous monitoring of these intelligent CV systems is required to achieve a trustworthy AI system in a zero-trust (ZT) environment. This paper introduces a novel two-stage framework that provides a mechanism towards achieving this monitoring for a ZT environment. We made use of Monte Carlo (MC) dropout with One-Class Classification techniques to propose a framework towards trustworthy AI systems for AVs. Through extensive experimentation with varying noise levels and number of MC samples, we demonstrate that our framework achieves promising results in anomaly detection. In particular, our framework explores the trade-off between detection accuracy and computational overhead, where we achieved a high FPS of 46.4 with MC size of 5 while the accuracy is as low as 61.5%. This study would provide us with valuable insights for real-world AV applications. https://journals.flvc.org/FLAIRS/article/view/138945 |
| spellingShingle | Chern Chao Tai Wesam Al Amiri Abhijeet Solanki Douglas Alan Talbert Nan Guo Syed Rafay Hasan Towards Trustworthy AI: Analyzing Model Uncertainty through Monte Carlo Dropout and Noise Injection Proceedings of the International Florida Artificial Intelligence Research Society Conference |
| title | Towards Trustworthy AI: Analyzing Model Uncertainty through Monte Carlo Dropout and Noise Injection |
| title_full | Towards Trustworthy AI: Analyzing Model Uncertainty through Monte Carlo Dropout and Noise Injection |
| title_fullStr | Towards Trustworthy AI: Analyzing Model Uncertainty through Monte Carlo Dropout and Noise Injection |
| title_full_unstemmed | Towards Trustworthy AI: Analyzing Model Uncertainty through Monte Carlo Dropout and Noise Injection |
| title_short | Towards Trustworthy AI: Analyzing Model Uncertainty through Monte Carlo Dropout and Noise Injection |
| title_sort | towards trustworthy ai analyzing model uncertainty through monte carlo dropout and noise injection |
| url | https://journals.flvc.org/FLAIRS/article/view/138945 |
| work_keys_str_mv | AT chernchaotai towardstrustworthyaianalyzingmodeluncertaintythroughmontecarlodropoutandnoiseinjection AT wesamalamiri towardstrustworthyaianalyzingmodeluncertaintythroughmontecarlodropoutandnoiseinjection AT abhijeetsolanki towardstrustworthyaianalyzingmodeluncertaintythroughmontecarlodropoutandnoiseinjection AT douglasalantalbert towardstrustworthyaianalyzingmodeluncertaintythroughmontecarlodropoutandnoiseinjection AT nanguo towardstrustworthyaianalyzingmodeluncertaintythroughmontecarlodropoutandnoiseinjection AT syedrafayhasan towardstrustworthyaianalyzingmodeluncertaintythroughmontecarlodropoutandnoiseinjection |