Potrojan: powerful neural-level trojan designs in deep learning models

M Zou, Y Shi, C Wang, F Li, WZ Song… - arXiv preprint arXiv …, 2018 - arxiv.org
With the popularity of deep learning (DL), artificial intelligence (AI) has been applied in many
areas of human life. Neural network or artificial neural network (NN), the main technique …

Optimizing weight value quantization for cnn inference

W Nogami, T Ikegami, R Takano… - 2019 International Joint …, 2019 - ieeexplore.ieee.org
The size and complexity of CNN models are increasing and as a result they are requiring
more computational and memory resources to be used effectively. Use of a lower bit width …

DCNNs: A Transfer Learning comparison of Full Weapon Family threat detection for Dual-Energy X-Ray Baggage Imagery

A Williamson, P Dickinson, T Lambrou… - arXiv preprint arXiv …, 2020 - arxiv.org
Recent advancements in Convolutional Neural Networks have yielded super-human levels
of performance in image recognition tasks [13, 25]; however, with increasing volumes of …