Autonomous Vehicle Security
Unraveling ML models for ensuring security
Research has demonstrated how these models are vulnerable to spoofing and adversarial examples resulting from small-magnitude perturbations in the input data. Therefore, understanding inputs (e.g., sensor data) is a critical step toward creating resilient infrastructure within which smart agents like CAVs and human actors can co-exist, thereby reducing risks to life and property.
About
Autonomous vehicles (AVs) are anticipated to have built-in AI systems for defending against cyberattacks. Machine learning (ML) models form the basis of many such AI systems. These models are notorious for acting like black boxes, transforming inputs into solutions with great accuracy, but no explanations support their decisions. Explanations are needed to communicate model performance, make decisions transparent, and establish trust in the models with stakeholders. Explanations can also indicate when humans must take control, for instance, when the ML model makes low-confidence decisions or offers multiple or ambiguous alternatives.
Get Started
Et enim pulvinar eget diam risus eget nulla eros non. Facilisi arcu ut commodo, tortor faucibus gravida urna magna. Blandit penatibus phasellus posuere quisque pellentesque adipiscing eget. Mi augue tristique nibh molestie fermentum, at. Fermentum, mauris nisi, feugiat convallis turpis enim eget. Sed eu sit nunc, sed. Scelerisque elit velit tempus duis tortor purus, non id aliquet. Ullamcorper vel magna magnis vitae orci sed vivamus. Posuere faucibus vitae velit egestas eleifend commodo commodo. Ornare blandit laoreet integer non.
Leo mauris blandit mi ac imperdiet posuere.
Project Lead and Members
Meet the Team >
Dr. Nidhi Rastogi
Praveen Chandrasekaran
Ajay Ashok Shewale
Dipkamal Bhusal
Contact to Contribute
Leo mauris blandit mi ac imperdiet posuere.
Duis nec nullam volutpat diam. Leo mauris blandit mi ac imperdiet posuere. Est facilisi nisi, turpis viverra mi arcu. Sed volutpat dui dignissim neque, venenatis natoque in. Et sem sed mauris porttitor. Pellentesque adipiscing quis sit sagittis est augue purus arcu. In diam purus semper pulvinar felis ut euismod malesuada. Pellentesque ipsum et turpis arcu viverra. Eros, amet in viverra accumsan.