Federated Learning-Based Privacy-Preserving Data Aggregation Scheme for IIoT

Abstract

The Industrial Internet of Things (IIoT) is the key technology of Industry 4.0. The combination of machine learning and IIoT has spawned a thriving smart industry. Machine learning models are trained and predicted based on raw data that contains sensitive information, and data sharing leads to information leakage. Data security and privacy protection in IIoT face serious challenges. Therefore, we propose a federated learning-based privacy-preserving data aggregation scheme (FLPDA) for IIoT. Data aggregation to protect individual user model changes in federated learning against reverse analysis attacks from industry administration centers. Each round of data aggregation uses the PBFT consensus algorithm to select an IIoT device from the aggregation area as the initialization and aggregation node. Paillier cryptosystem and secret sharing are combined to realize data fault tolerance and secure sharing. Security analysis and performance evaluation show that the scheme can effectively protect data privacy and resist various attacks. It has lower communication, computational, and storage overhead than existing schemes.

A Data Attack Detection Framework for Cryptography-Based Secure Aggregation Methods in 6G Intelligent Applications

“…For Paillier Encryption [36], given two ciphertexts, anyone can compute the ciphertext of their sum without access to the original plaintexts.…”

“…Blockchain [40] √ √ ZKP [35] and SMPC [36] emphasize the correctness of data processing and privacy protection, and Paillier also performs well in these aspects, with advantages in scalability. MTH [38] and ATH [39] excel in efficiency but may require compromises in other areas.…”

“…We use the homomorphic Paillier encryption algorithm [36] to protect data privacy, implement data integrity auditing based on a homomorphic hash algorithm, and demonstrate its feasibility. The security parameters of the Paillier encryption algorithm and the homomorphic hash algorithm are set to 1024, where the modulus n in the Paillier encryption algorithm and the multiplication homomorphic hash function H 2 (x) is a 1024-bit large prime number, and the modulus p in the addition homomorphic hash function H 1 (x) is a 1024-bit large prime number.…”

“…The security parameters of the Paillier encryption algorithm and the homomorphic hash algorithm are set to 1024, where the modulus n in the Paillier encryption algorithm and the multiplication homomorphic hash function H 2 (x) is a 1024-bit large prime number, and the modulus p in the addition homomorphic hash function H 1 (x) is a 1024-bit large prime number. Performance evaluation of the Paillier encryption algorithm [36] and the homomorphic hash algorithm shows that the time consumption for data integrity verification remains within a relatively low range.…”

FPGA versus GPU for accelerating homomorphic encryption in federated learning

“…With the increasing use of machine learning, data privacy and protection have become more important. federated Learning, as a machine learning scheme that allows for training data to be kept confidential, has been adopted to enhance data security [1][2][3] [4]. However, the implementation of special methods, such as Secure Multi-party Computing, Differential Privacy, and homomorphic encryption, are necessary to provide this security.…”