Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher.
Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?
Some links on this page may take you to non-federal websites. Their policies may differ from this site.
In the past decade, Deep Learning (DL) systems have been widely deployed in various application domains to facilitate our daily life, e.g., natural language processing, healthcare, activity recognition, and autonomous driving. Meanwhile, it is extremely challenging to ensure the correctness of DL systems (e.g., due to their intrinsic nondeterminism), and bugs in DL systems can cause serious consequences and may even threaten human lives. In the literature, researchers have explored various techniques to test, analyze, and verify DL models, since their quality directly affects the corresponding system behaviors. Recently, researchers have also proposed novel techniques for testing the underlying operator-level DL libraries (such as TensorFlow and PyTorch), which provide general binary implementations for each high-level DL operator and are the foundation for running DL models on different hardware platforms. However, there is still limited work targeting the reliability of the emerging tensor compilers (also known as DL compilers), which aim to automatically compile high-level tensor computation graphs directly into high-performance binaries for better efficiency, portability, and scalability than traditional operator-level libraries. Therefore, in this paper, we target the important problem of tensor compiler testing, and have proposed Tzer, a practical fuzzing technique for the widely used TVM tensor compiler. Tzermore »Free, publicly-accessible full text available April 29, 2023
Atomically dispersed iron sites with a nitrogen–carbon coating as highly active and durable oxygen reduction catalysts for fuel cellsFree, publicly-accessible full text available July 1, 2023
Abstract The implementation of body-worn cameras (BWC) by policing agencies has received widespread support from many individuals, including citizens and police officers. Despite their increasing prevalence, little is known about how the point-of-view (POV) of these cameras affects perceptions of viewers. In this research, we investigate how POV interacts with skin color of citizens in police use of force videos to affect perceptions of procedural justice. In an experimental study, participants watched eight police use of force videos—half recorded from BWC and half from an onlooker’s perspective—in which skin tone of the citizen varied. Results indicate that POV interacts with citizen skin tone such that, compared to the onlooker perspective, the BWC exacerbated viewer racial bias against dark skin tone citizens. Furthermore, identification with the police officer fully mediated this relationship. Results are discussed in relation to media theory and practical implications.