J. Hu
4 Papers
J. Hu is an academic researcher. The author has contributed to research in topics: Computer science & Simulated annealing. The author has co-authored 3 publications.
Chat about Author
Papers
Anomaly-Based Intrusion on IoT Networks Using AIGAN-a Generative Adversarial Network
Zhipeng Liu,J. Hu,Yang Liu,Kaushik Roy,Xiaohong Yuan,Jinsheng Xu +5 more
TL;DR: A generative adversarial network (GAN) in AIGAN is developed, which uses deep learning techniques to generate adversarial data and to conduct an anomaly attack on IoT networks.
6
Competition in the Cryptocurrency Exchange Market
J. Hu,Anthony Lee Zhang +1 more
TL;DR: In this paper , the authors show that when large exchanges list new tokens, trade volumes on small exchanges increase, and small exchanges become more likely to list, and rationalize these facts in a model where small exchanges have captive customer bases, and rely on arbitrage trade with large exchanges for liquidity provision.
1
Dynamical Isometry based Rigorous Fair Neural Architecture Search
TL;DR: Zhang et al. as discussed by the authors proposed a novel neural architecture search algorithm based on dynamical isometry, which uses the fix point analysis method in the mean field theory to analyze the dynamics behavior in the steady state random neural network, and how dynamic isometry guarantees the fairness of weight sharing based NAS.
Fast black box attack of face recognition system based on metaheuristic simulated annealing
Yao Wang,Chuang Lu,J. Hu,Yi Zhang,Hongying Lu +4 more
- 31 May 2023
TL;DR: SA-Attack as discussed by the authors generates adversarial samples which cannot be distinguished by human within very limited queries and can successfully attack advanced face recognition models, including public and commercial solutions, which proves the practicability of the method.