Secure and Efficient Coded Multi-Access Edge Computing With Generalized Graph Neural Networks
Open accessThe DOI matches its Crossref record; 72 of the 72 references it cites were found in a registry or an index.
Abstract
We formulate a novel framework to improve security and utility of the coded multi-access edge computing (MEC) network for Internet of Things (IoT) applications where multiple edge servers (ESs) jointly process raw IoT data to obtain the final network output. To correctly recover the final output even when some processing outputs produced by malicious or malfunctioning ESs are erroneous, the network utilizes coded distributed computing (CDC) that enhances security by adding computational redundancy to the data processed by ESs. Within the framework, we propose an advanced approach to address limitations of contemporary CDC-based systems related to their inability to guarantee security when the number of malicious ESs is large and reduced network utility due to redundant computations. In this approach, the processing loads are allocated to ESs based on deep learning (DL) algorithms to identify the unknown ESs’ types (faithful or malicious) and minimize the load of malicious ESs, thereby optimizing security and utility. The proposed DL algorithms adopt the message passing neural network (NN) – a generalized graph NN with lower complexity and faster convergence than conventional NNs. We prove that our framework yields the optimal security and utility, and verify its superior performance compared with the state-of-the-art schemes.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Additionally, blockchain can securely manage identities and access permissions, which is essential for multiple devices owned by different users7.”
From Blockchain-based secure MEC model for VANETs using hybrid networks (2025) · cites this paper as [7]
Citations
Cites
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225 · cited 2×
“…although from Propositions 2 and 4, both the SL and RL algorithms converge (exponentially fast) to the stable states regardless of the settings of the decay and discount factors h and g , these settings can still significantly affect the convergence time of the algorithms [23], [59], [60].”
BackgroundMethodSemi-supervised classification with graph convolutional networks
Kipf, T. N., & Welling, M. (2016) · arXiv · doi:10.48550/arxiv.1609.02907 · Cited by 24,853 · cited 1×
“Various GNN models have already been used in solving certain scientific problems, including knowledge graph completion [24], text/video recognition [39], [40], [41], protein surface estimation [42], combinatorial optimization [43], social network analysis [44], [45], physical system representation [46], [47], vehicula…”
MethodNeural Networks for Pattern Recognition
Bishop, C. M. (1995) · doi:10.1093/oso/9780198538493.001.0001 · Cited by 12,287
Wang, X., Girshick, R., Gupta, A., & He, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00813 · Cited by 11,596
The graph neural network model
Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M., & Monfardini, G. (2009) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2008.2005605 · Cited by 9,582 · cited 4×
“Briefly, compared to most NNs, the MPNN yields the faster convergence and lower time complexity, and can be used in the systems (similar to the coded MEC) where the node outputs cannot be verified locally [23], [24], [25], [26], [27].”
BackgroundInfluentialMarkov decision processes: Discrete stochastic dynamic programming
Hazeghi, K., & Puterman, M. L. (1995) · Journal of the American Statistical Association · doi:10.2307/2291177 · Cited by 8,037 · cited 5×
“…satisfying the Bellman optimality equation in (21) can be solved by combining the online training of our MPNN-based model with dynamic programming [59], i.e., through recursive combination of i) the Bellman equation, ii) hidden state/ weight updates according to the MPNN framework, and iii) value…”
BackgroundMethodInfluentialOn the Properties of Neural Machine Translation: Encoder–Decoder Approaches
Cho, K., van Merrienboer, B., Bahdanau, D., & Bengio, Y. (2014) · Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation · doi:10.3115/v1/w14-4012 · Cited by 7,099 · cited 3×
“…Þ at round t ; z vt 2 ð 0 ; 1 Þ and h vt 2 ð(cid:6) 1 ; 1 Þ are the update and candidate activation gates of the node, given by [58] In (13b) and (13c), y vt 2 ð 0 ; 1 Þ is the reset gate , given by [58] ’ z and ’ y are NNs (with learned weights ^W H ) for the update and reset gates, respectively.”
BackgroundMethodInfluentialGraph neural networks: A review of methods and applications
Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., & Sun, M. (2020) · AI Open · doi:10.1016/j.aiopen.2021.01.001 · Cited by 6,880
Neural Message Passing for Quantum Chemistry
Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O., & Dahl, G. E. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.01212 · Cited by 3,440 · cited 10×
“Recently, there has been a surge of interest in the design of GNNs – DL models extending NNs to process complex non-Euclidean graph-like data spaces [23], [24], [25], [26], [27].”
BackgroundMethodResultInfluentialGraph Convolutional Networks for Text Classification
Yao, L., Mao, C., & Luo, Y. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33017370 · Cited by 1,983
Research works printed but not linked: 4
- jothi, 2021, WILS-TRS—A novel optimized deep learning based intrusion detection framework for IoT networks, Pers Ubiquitous Comput, 1
- takabi, 2016, Privacy preserving multi-party machine learning with homomorphic encryption, Proc Int Conf Neural Inf Process, 1
- taguchi, 2004, Computer-Based Robust Engineering Essentials for Dfss [M]
- goodfellow, 2016, Deep Learning
Cited by
Saravanan, T., & Saravanakumar, S. (2022) · International Journal of Intelligent Networks · doi:10.1016/j.ijin.2022.11.002 · Cited by 84
Graph Neural Networks for Next-Generation-IoT: Recent Advances and Open Challenges
Tung, N. X., Giang, L. T., Son, B. D., Geun-Jeong, S., Chien, T. V., Hanzo, L., & Hwang, W.-J. (2025) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3613845 · Cited by 61
“Similarly, Asheralieva and Niyato [54] model MEC networks relying on multiple edge servers as a directed multigraph, where the GNN produces a graph-level embedding used for managing security and efficiency.”
Anomaly detection using deep convolutional generative adversarial networks in the internet of things
Mishra, A. K., Paliwal, S., & Srivastava, G. (2023) · ISA Transactions · doi:10.1016/j.isatra.2023.12.005 · Cited by 54
Asheralieva, A., Niyato, D. T., & Miyanaga, Y. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2023.3262514 · Cited by 39
Self-citationAsheralieva, A., Niyato, D. T., & Wei, X. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3298789 · Cited by 24
Self-citation
Metadata
- Authors
- Asheralieva, A., & Niyato, D.
- Affiliations
- Southern University of Science and Technology (CN)
- Nanyang Technological University (SG)
- Venue
- IEEE Transactions on Mobile Computing
- Published
- 2023-09-01
- Volume
- 22
- Issue
- 9
- Pages
- 5504-5524
- ISSN
- 1536-1233 (ISSN-L)
- 1558-0660
- 2161-9875
- OpenAlex
- W4285114235
- Cited by
- 15
- References
- 70
- Citations by year
- 2026: 2 · 2025: 5 · 2024: 2 · 2023: 4
- FWCI
- 1.44
- Type
- journal article
- Language
- en
- Open access
- green
- figshare.com
- Licence
- Locations
- IEEE Transactions on Mobile Computing (publishedVersion)
- DR-NTU (Nanyang Technological University) (submittedVersion)
- Figshare (submittedVersion, cc-by)
- Funders
- National Natural Science Foundation of China (61950410603)
- Department of Education of Guangdong Province (2021KTSCX110)
- Programme DesCartes and National Research Foundation
- Alibaba Group
- Alibaba-NTU Singapore Joint Research Institute
- National Research Foundation Singapore (AISG2-RP-2020-019)
- Ministry of Education - Singapore (RG16/20)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Computer Networks and Communications › Cryptography and Data Security
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Keywords
- mobile edge computing, coded distributed computing, Internet of Things, fault tolerance, graph neural networks, message passing neural networks, load allocation, computational redundancy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.