Hardware accelerators are essential to the accommodation of ever-increasing Deep Neural Network (DNN) workloads on the resource-constrained embedded devices. While accelerators facilitate fast and energy-efficient DNN operations, their accuracy is threatened by faults in their on-chip and off-chip memories, where millions of DNN weights are held. Our research project aims to investigate, characterize, and mitigate errors in the DNN accelerators that may originate from process variation, aging, and/or fault injection attacks. This talk introduces our recent contributions on defect-aware deployment, on-line self-monitoring of accelerator healthiness, and on-line detection of fault injection attacks.