VU ISIS researchers win Best Paper Award at the Workshop on Assured Autonomous Systems (WAAS)

The best paper award at the recently concluded Workshop on Assured Autonomous Systems (WAAS), part of the 41st IEEE Symposium on Security and Privacy, was awarded to researchers from ISIS/Vanderbilt University. The title of the paper is "Trusted Confidence Bounds for Learning Enabled Cyber-Physical Systems" and was authored by Dimitrios Boursinos and Dr. Xenofon Koutsoukos. The WAAS Best Paper Award recognizes the paper that exhibits key contributions in the field of assured autonomy.

Cyber-physical systems (CPS) can benefit by the use of learning enabled components (LECs) such as deep neural networks (DNNs) for perception and decision making tasks. However, DNNs are typically non-transparent making reasoning about their predictions very difficult, and hence their application to safety-critical systems is very challenging. LECs could be integrated easier into CPS if their predictions could be complemented with a confidence measure that quantifies how much we trust their output. The paper presents an approach for computing confidence bounds based on Inductive Conformal Prediction (ICP). We train a Triplet Network architecture to learn representations of the input data that can be used to estimate the similarity between test examples and examples in the training data set. Then, these representations are used to estimate the confidence of set predictions from a classifier that is based on the neural network architecture used in the triplet. The approach is evaluated using a robotic navigation benchmark and the results show that we can computed trusted confidence bounds efficiently in real-time.

Dimitrios Boursinos is a 4th year PhD candidate at the Institute for Software Integrated Systems (ISIS) in the Department of EECS at Vanderbilt. His research focuses on  assurance monitors that provide safety guaranties for classification machine learning models. He is advised by Prof. Xenofon Koutsoukos.