Prinkle Sharma
Papers
1
Total Citations
63
H-Index
1
About
Prinkle Sharma is a leading researcher at the intersection of machine learning security and autonomous systems, with a primary focus on adversarial machine learning in safety-critical environments. Her seminal 2019 work, "Attacks on Machine Learning: Adversarial Examples in Connected and Autonomous Vehicles" (63 citations), fundamentally exposed how subtle perturbations to sensor inputs can deceive ML models controlling driverless cars, threatening traffic efficiency, passenger safety, and road security. This research established a critical framework for understanding vulnerabilities in autonomous vehicle perception systems, demonstrating that adversarial examples—imperceptible to humans—could cause misclassification of traffic signs, pedestrians, or obstacles. Sharma’s contributions have shaped defensive strategies in CAV cybersecurity, influencing both academic research and industry safety standards. Her work bridges the gap between theoretical adversarial ML and real-world deployment risks, earning recognition for its practical urgency. By highlighting these attack vectors, she has driven the development of robust, resilient AI systems for transportation, making her a pivotal voice in ensuring that autonomous vehicles remain secure against emerging threats.
Research Focus
Key Achievements
Top Papers
- 1