Yanjing Li
Papers
1
Total Citations
17
H-Index
1
About
Yanjing Li is a leading researcher at the intersection of hardware security, reliable computing, and deep learning systems. Her most impactful work focuses on ensuring the dependability of specialized hardware, particularly deep learning accelerators, through novel in-field testing methodologies. In her highly cited 2021 paper, Li introduced a technique for generating efficient, functional self-tests that can be applied during a DL accelerator's normal operation—a critical contribution for meeting stringent safety and reliability requirements in autonomous systems and other high-stakes applications. This work, which has garnered 17 citations, addresses a fundamental challenge: how to verify hardware integrity without disrupting performance. Beyond this flagship contribution, Li’s broader research portfolio spans hardware Trojan detection, side-channel analysis, and fault-tolerant architectures. Her innovative approaches have been recognized with multiple best paper nominations and have influenced both academic research and industrial design practices. For students and researchers, Li’s work offers a compelling model of how to bridge the gap between theoretical reliability and practical, deployable solutions in the age of ubiquitous AI.
Research Focus
Key Achievements
Top Papers
- 1Efficient Functional In-Field Self-Test for Deep Learning Accelerators17 citations · 2021