Edge Computing Assisted an Efficient Privacy Protection Layered Data Aggregation Scheme for IIoT

The emergence of edge computing has improved the real time and efficiency of the Industrial Internet of Things. In order to achieve safe and efficient data collection and application in the Industrial Internet of Things, a lot of computing and bandwidth resources are usually sacrificed. From the perspective of low computing and communication overhead, this paper proposes an efficient privacy protection layered data aggregation scheme for edge computing assisted IIoT by combining the Chinese Remainder Theorem (CRT), improved Paillier homomorphic algorithm, and hash chain technology (edge computing assisted an efficient privacy protection layered data aggregation scheme for IIoT, EE-PPDA). In EE-PPDA, first, a layered aggregation architecture based on edge computing is designed. Edge nodes and cloud are responsible for local aggregation and global aggregation, respectively, which effectively reduces the amount of data transmission. At the same time, EE-PPDA achieves data confidentiality through improved Paillier encryption, ensuring that neither attackers nor semitrusted nodes (e.g., edge nodes and clouds) can know the private data of a single device, and it can resist by simply using hash chains to resist tampering and pollution attacks ensure data integrity. Second, according to the CRT, the cloud can obtain the fine-grained aggregation results of subregions from the global aggregation results, thereby providing fine-grained data services. In addition, the EE-PPDA scheme also supports fault tolerance. Even if some IIoT devices or communication links fail, the cloud can still decrypt incomplete aggregated ciphertexts and obtain the expected aggregation results. Finally, the performance evaluation shows that the proposed EE-PPDA scheme has less calculation and communication costs.

Download Full-text

Towards Communication-Efficient and Attack-Resistant Federated Edge Learning for Industrial Internet of Things

ACM Transactions on Internet Technology ◽

10.1145/3453169 ◽

2022 ◽

Vol 22 (3) ◽

pp. 1-22

Author(s):

Yi Liu ◽

Ruihui Zhao ◽

Jiawen Kang ◽

Abdulsalam Yassine ◽

Dusit Niyato ◽

...

Keyword(s):

Internet Of Things ◽

Data Privacy ◽

Differential Privacy ◽

Global Model ◽

Edge Computing ◽

Communication Overhead ◽

Industrial Internet Of Things ◽

Malicious Nodes ◽

Industrial Internet ◽

Communication Efficiency

Federated Edge Learning (FEL) allows edge nodes to train a global deep learning model collaboratively for edge computing in the Industrial Internet of Things (IIoT), which significantly promotes the development of Industrial 4.0. However, FEL faces two critical challenges: communication overhead and data privacy. FEL suffers from expensive communication overhead when training large-scale multi-node models. Furthermore, due to the vulnerability of FEL to gradient leakage and label-flipping attacks, the training process of the global model is easily compromised by adversaries. To address these challenges, we propose a communication-efficient and privacy-enhanced asynchronous FEL framework for edge computing in IIoT. First, we introduce an asynchronous model update scheme to reduce the computation time that edge nodes wait for global model aggregation. Second, we propose an asynchronous local differential privacy mechanism, which improves communication efficiency and mitigates gradient leakage attacks by adding well-designed noise to the gradients of edge nodes. Third, we design a cloud-side malicious node detection mechanism to detect malicious nodes by testing the local model quality. Such a mechanism can avoid malicious nodes participating in training to mitigate label-flipping attacks. Extensive experimental studies on two real-world datasets demonstrate that the proposed framework can not only improve communication efficiency but also mitigate malicious attacks while its accuracy is comparable to traditional FEL frameworks.

Download Full-text