Felipe Toledo (MSc)

Felipe Toledo (MSc)

Ph.D student at the University of Virginia. Interested in AI and Deep Neural Network verification

Publications

Specifying and Monitoring Safe Driving Properties with Scene Graphs

Felipe Toledo, Trey Woodlief, Sebastian Elbaum, and Matthew B. Dwyer

With the proliferation of autonomous vehicles (AVs) comes the need to ensure they abide to safe driving properties. Specifying and monitoring such properties, however, is challenging because of the mismatch between the semantic space over which typical driving properties are asserted (e.g., vehicles, pedestrians, intersections) and the sensed inputs of…
Read more

Content: [Pre-print] [Artifact] [Video]

S3C Spatial Semantic Scene Coverage for Autonomous Vehicles

Trey Woodlief, Felipe Toledo, Sebastian Elbaum, and Matthew B. Dwyer

Autonomous vehicles (AVs) must be able to operate in a wide range of scenarios including those in the long tail distribution that include rare but safety-critical events. The collection of sensor input and expected output datasets from such scenarios is crucial for the development and testing of such systems. Yet,…
Read more

Content: [Pre-print] [Paper] [Artifact]

Deeper Notions of Correctness in Image-Based DNNs: Lifting Properties from Pixel to Entities

Felipe Toledo, David Shriver, Sebastian Elbaum, and Matthew B. Dwyer

Deep Neural Networks (DNNs) that process images are being widely used for many safety-critical tasks, from autonomous vehicles to medical diagnosis. Currently, DNN correctness properties are defined at the pixel level over the entire input. Such properties are useful to expose system failures related to sensor noise or adversarial attacks,…
Read more

Content: [Pre-print] [Paper] [Video]

Distribution Models for Falsification and Verification of DNNs

Felipe Toledo, David Shriver, Sebastian Elbaum, and Matthew B. Dwyer

DNN validation and verification approaches that are input distribution agnostic waste effort on irrelevant inputs and report false property violations. Drawing on the large body of work on model-based validation and verification of traditional systems, we introduce the first approach that leverages environmental models to focus DNN falsification and verification…
Read more

Content: [Paper] [Appendix] [Artifact] [Video]