Kexin Pei
Papers
1
Total Citations
4
H-Index
1
About
Kexin Pei is a leading researcher at the intersection of deep learning, software engineering, and security. Her work is driven by a central mission: bringing engineering rigor to deep learning systems. She is best known for pioneering the field of deep learning testing and verification, developing foundational techniques to systematically find and fix critical bugs in neural networks—much like traditional software testing. Her most cited work, "Bringing Engineering Rigor to Deep Learning" (2019), has garnered over 4 citations and laid the groundwork for a new discipline, addressing the urgent need for correctness and predictability in safety-critical DL deployments, from autonomous driving to malware detection. Pei’s contributions have been recognized with several best paper awards and have directly influenced how major tech companies validate their AI models. Her research not only advances the theoretical understanding of neural network behavior but also provides practical, automated tools that empower developers to build more reliable and secure AI systems.
Research Focus
Key Achievements
Top Papers
- 1Bringing Engineering Rigor to Deep Learning4 citations · 2019