| Title | Privacy-Preserving Outsourced Speech Recognition for Smart IoT Devices |
| Publication Type | Journal Article |
| Year of Publication | 2019 |
| Authors | Ma, Zhuo, Liu, Yang, Liu, Ximeng, Ma, Jianfeng, Li, Feifei |
| Journal | IEEE Internet of Things Journal |
| Volume | 6 |
| Pagination | 8406–8420 |
| ISSN | 2327-4662 |
| Keywords | additive secret sharing-based interactive protocols, Back propagation through time (BPTT), composability, cryptography, data privacy, distributed processing, edge computing, forward propagation (FP), human-machine interaction interface, intelligent IoT device voice control, Internet of Things, Logic gates, long short-term memory (LSTM), long short-term memory neural network, neural network-based speech recognition, Neural networks, outsourced privacy-preserving speech recognition framework, privacy, privacy leakage, Privacy-preserving, privacy-preserving outsourced speech recognition, Protocols, pubcrawl, recurrent neural nets, smart Internet of Things (IoT) devices, smart IoT devices, Speech recognition |
| Abstract | Most of the current intelligent Internet of Things (IoT) products take neural network-based speech recognition as the standard human-machine interaction interface. However, the traditional speech recognition frameworks for smart IoT devices always collect and transmit voice information in the form of plaintext, which may cause the disclosure of user privacy. Due to the wide utilization of speech features as biometric authentication, the privacy leakage can cause immeasurable losses to personal property and privacy. Therefore, in this paper, we propose an outsourced privacy-preserving speech recognition framework (OPSR) for smart IoT devices in the long short-term memory (LSTM) neural network and edge computing. In the framework, a series of additive secret sharing-based interactive protocols between two edge servers are designed to achieve lightweight outsourced computation. And based on the protocols, we implement the neural network training process of LSTM for intelligent IoT device voice control. Finally, combined with the universal composability theory and experiment results, we theoretically prove the correctness and security of our framework. |
| DOI | 10.1109/JIOT.2019.2917933 |
| Citation Key | ma_privacy-preserving_2019 |
Privacy-Preserving Outsourced Speech Recognition for Smart IoT Devices