Zobrazeno 1 - 10
of 258
pro vyhledávání: '"Zheng, Haibin"'
Benefiting from well-trained deep neural networks (DNNs), model compression have captured special attention for computing resource limited equipment, especially edge devices. Knowledge distillation (KD) is one of the widely used compression technique
Externí odkaz:
http://arxiv.org/abs/2406.03409
Autor:
Chen, Jinyin, Ge, Jie, Zheng, Shilian, Ye, Linhui, Zheng, Haibin, Shen, Weiguo, Yue, Keqiang, Yang, Xiaoniu
A wireless communications system usually consists of a transmitter which transmits the information and a receiver which recovers the original information from the received distorted signal. Deep learning (DL) has been used to improve the performance
Externí odkaz:
http://arxiv.org/abs/2309.16706
Deep neural networks (DNNs) have demonstrated their outperformance in various software systems, but also exhibit misbehavior and even result in irreversible disasters. Therefore, it is crucial to identify the misbehavior of DNN-based software and imp
Externí odkaz:
http://arxiv.org/abs/2307.09375
Deep neural networks (DNNs) are vulnerable to adversarial examples, which may lead to catastrophe in security-critical domains. Numerous detection methods are proposed to characterize the feature uniqueness of adversarial examples, or to distinguish
Externí odkaz:
http://arxiv.org/abs/2303.18131
Autor:
Chen, Jinyin, Zheng, Haibin, Liu, Tao, Li, Rongchang, Cheng, Yao, Zhang, Xuhong, Ji, Shouling
With the development of deep learning processors and accelerators, deep learning models have been widely deployed on edge devices as part of the Internet of Things. Edge device models are generally considered as valuable intellectual properties that
Externí odkaz:
http://arxiv.org/abs/2303.12397
Federated learning (FL), an effective distributed machine learning framework, implements model training and meanwhile protects local data privacy. It has been applied to a broad variety of practice areas due to its great performance and appreciable p
Externí odkaz:
http://arxiv.org/abs/2303.10399
Widespread applications of deep neural networks (DNNs) benefit from DNN testing to guarantee their quality. In the DNN testing, numerous test cases are fed into the model to explore potential vulnerabilities, but they require expensive manual cost to
Externí odkaz:
http://arxiv.org/abs/2211.00273
Graph neural network (GNN) with a powerful representation capability has been widely applied to various areas, such as biological gene prediction, social recommendation, etc. Recent works have exposed that GNN is vulnerable to the backdoor attack, i.
Externí odkaz:
http://arxiv.org/abs/2210.13710
Link prediction, inferring the undiscovered or potential links of the graph, is widely applied in the real-world. By facilitating labeled links of the graph as the training data, numerous deep learning based link prediction methods have been studied,
Externí odkaz:
http://arxiv.org/abs/2208.06776
The proliferation of fake news and its serious negative social influence push fake news detection methods to become necessary tools for web managers. Meanwhile, the multi-media nature of social media makes multi-modal fake news detection popular for
Externí odkaz:
http://arxiv.org/abs/2206.08788