J
Jingtao Li
Researcher at Arizona State University
Publications - 34
Citations - 308
Jingtao Li is an academic researcher from Arizona State University. The author has contributed to research in topics: Computer science & Engineering. The author has an hindex of 7, co-authored 20 publications receiving 155 citations. Previous affiliations of Jingtao Li include King Abdullah University of Science and Technology & University of Electronic Science and Technology of China.
Papers
More filters
Journal ArticleDOI
Valence and conduction band offsets of β-Ga2O3/AlN heterojunction
Haiding Sun,C. G. Torres Castanedo,Kaikai Liu,Kuang-Hui Li,Wenzhe Guo,Ronghui Lin,Xinwei Liu,Jingtao Li,Xiaohang Li +8 more
TL;DR: In this paper, a very thin β-Ga2O3 layer was deposited on an AlN/sapphire template to form the heterojunction by pulsed laser deposition.
Proceedings ArticleDOI
Defending and Harnessing the Bit-Flip Based Adversarial Weight Attack
TL;DR: The experiments show that, for BFA to achieve the identical prediction accuracy degradation (e.g., below 11\% on CIFAR-10), it requires 19.3x and 480.1x more effective malicious bit-flips on ResNet-20 and VGG-11 respectively, compared to defend-free counterparts.
Journal ArticleDOI
Wurtzite BAlN and BGaN alloys for heterointerface polarization engineering
Kaikai Liu,Haiding Sun,Feras AlQatari,Wenzhe Guo,Xinwei Liu,Jingtao Li,Carlos G Torres Castanedo,Xiaohang Li +7 more
TL;DR: In this article, the spontaneous polarization and piezoelectric constants of BxAl1-xN (BAlN) and BxGa1-n (BGaN) ternary alloys were calculated with the hexagonal structure as reference.
Proceedings ArticleDOI
Defending Bit-Flip Attack through DNN Weight Reconstruction
Jingtao Li,Adnan Siraj Rakin,Yan Xiong,Liangliang Chang,Zhezhi He,Deliang Fan,Chaitali Chakrabarti +6 more
TL;DR: This work proposes a novel weight reconstruction method as a countermeasure to adversarial attacks on neural network weights, specifically, during inference, the weights are reconstructed such that the weight perturbation due to BFA is minimized or diffused to the neighboring weights.
Posted Content
T-BFA: Targeted Bit-Flip Adversarial Weight Attack
TL;DR: This paper proposes the first work of targetedBFA based (T-BFA) adversarial weight attack on DNN models, which can intentionally mislead selected inputs to a target output class through a novel class-dependent weight bit ranking algorithm.