Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Qinkai Zheng"'
Publikováno v:
AI Open, Vol 3, Iss , Pp 218-228 (2022)
Graph neural networks (GNNs) have been widely adopted for modeling graph-structure data. Most existing GNN studies have focused on designing different strategies to propagate information over the graph structures. After systematic investigations, we
Externí odkaz:
https://doaj.org/article/1921397abd5c451ca0d982648af759f3
Publikováno v:
Database Systems for Advanced Applications ISBN: 9783031306778
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::77dc8ec412d27c4db8cccfbeabd81c3b
https://doi.org/10.1007/978-3-031-30678-5_34
https://doi.org/10.1007/978-3-031-30678-5_34
Publikováno v:
IEEE Transactions on Intelligent Transportation Systems
IEEE Transactions on Intelligent Transportation Systems, 2020
IEEE Transactions on Intelligent Transportation Systems, IEEE, 2020, pp.1-10. ⟨10.1109/TITS.2020.3032882⟩
IEEE Transactions on Intelligent Transportation Systems, 2020
IEEE Transactions on Intelligent Transportation Systems, IEEE, 2020, pp.1-10. ⟨10.1109/TITS.2020.3032882⟩
With the development of modern Intelligent Transportation System (ITS), reliable and efficient transportation information sharing becomes more and more important. Although there are promising wireless communication schemes such as Vehicle-to-Everythi
Publikováno v:
IEEE Internet of Things Journal. 8:3180-3188
The rapid development of deep learning (DL) enables resource-constrained systems and devices [e.g., Internet of Things (IoT)] to perform sophisticated artificial intelligence (AI) applications. However, AI models, such as deep neural networks (DNNs),
Graph Neural Networks (GNNs) have achieved promising performance in various real-world applications. However, recent studies have shown that GNNs are vulnerable to adversarial attacks. In this paper, we study a recently-introduced realistic attack sc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c7f62ec078689a3ec980846ba52beff8
http://arxiv.org/abs/2106.06663
http://arxiv.org/abs/2106.06663
Publikováno v:
Smart Computing and Communication
Smart Computing and Communication, Oct 2019, Birmingham, United Kingdom. pp.266-276, ⟨10.1007/978-3-030-34139-8_26⟩
Lecture Notes in Computer Science ISBN: 9783030341381
SmartCom
Smart Computing and Communication, Oct 2019, Birmingham, United Kingdom. pp.266-276, ⟨10.1007/978-3-030-34139-8_26⟩
Lecture Notes in Computer Science ISBN: 9783030341381
SmartCom
With the deployment of multimedia compression techniques, contents such as images or videos are transmitted through resource-constrained networks such as Internet of Things (IoT) scenarios. Traditional multimedia compression methods based on spatial-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b3ce08bc5d5c28d2376d64eaad18ac3b
https://hal.telecom-paris.fr/hal-02450312
https://hal.telecom-paris.fr/hal-02450312
Publikováno v:
IEEE Transactions on Computers. :1-1
Deep Neural Networks are well-known to be vulnerable to Adversarial Examples. Recently, advanced gradient-based attacks were proposed (e.g., BPDA and EOT), which can significantly increase the difficulty and complexity of designing effective defenses
Publikováno v:
IEEE Transactions on Industrial Informatics. :1-1
With the development of big data and network technology, there are more use cases, such as edge computing, that require more secure and efficient multimedia big data transmission. Data compression methods can help achieving many tasks like providing