Explainable AI for Transparent Decision-Making in Cybersecurity Operations for Autonomous Vehicles
Keywords:
Connected autonomous vehicles (CAVs)Abstract
Connected autonomous vehicles (CAVs), integrating connected vehicles and autonomous vehicles, demonstrate a use case of how advanced simulations and machine learning were combined to improve the decision-making capabilities for a holistic system CO3. CAVs are influenced by results obtained from adversarial research done on common sensor modalities (radar, camera and Lidar) integrated into them to take decisions related to perception and fusion. The output of perception acts as an input to control decision-making algorithms governing the movement of the CAV. Vulnerabilities have been identified in each common sensor modality which can change the decision-making of the algorithm [1]. The top three modalities (camera, radar, lidar) used in self-driving vehicles are shown to be inter-dependent with correlation analysis, the same information can be used to fool the system to trigger misclassification by both adding different real-word noise. Different factors that affect perception and decision-making were individually tested and demonstrated to affect the decision of the CAV.
Downloads
References
Tatineni, S., and A. Katari. “Advanced AI-Driven Techniques for Integrating DevOps and MLOps: Enhancing Continuous Integration, Deployment, and Monitoring in Machine Learning Projects”. Journal of Science & Technology, vol. 2, no. 2, July 2021, pp. 68-98, https://thesciencebrigade.com/jst/article/view/243.
Shahane, Vishal. "Optimizing Cloud Resource Allocation: A Comparative Analysis of AI-Driven Techniques." Advances in Deep Learning Techniques 3.2 (2023): 23-49.
Abouelyazid, Mahmoud. "Comparative Evaluation of SORT, DeepSORT, and ByteTrack for Multiple Object Tracking in Highway Videos." International Journal of Sustainable Infrastructure for Cities and Societies 8.11 (2023): 42-52.
Prabhod, Kummaragunta Joel. "Advanced Techniques in Reinforcement Learning and Deep Learning for Autonomous Vehicle Navigation: Integrating Large Language Models for Real-Time Decision Making." Journal of AI-Assisted Scientific Discovery 3.1 (2023): 1-20.
Tatineni, Sumanth, and Sandeep Chinamanagonda. “Leveraging Artificial Intelligence for Predictive Analytics in DevOps: Enhancing Continuous Integration and Continuous Deployment Pipelines for Optimal Performance”. Journal of Artificial Intelligence Research and Applications, vol. 1, no. 1, Feb. 2021, pp. 103-38, https://aimlstudies.co.uk/index.php/jaira/article/view/104.
