Sensor data protection method and system, computer equipment and intelligent terminal

Abstract

The invention belongs to the technical field of information data security, and discloses a sensor data protection method and system, a computer device and an intelligent terminal, a random walk algorithm and a training method of a generative adversarial network are adopted, a user does not need to define a specific action sequence or consume local computing resources to perform data synthesis, and the user experience is improved. A user only needs to define the proportion of each action before use and then submits predefined data to a cloud server, the cloud server completes action sequence construction and multi-sensor simulation data generation, and a simulation data set formed by combination of the simulation data and the action sequence is submitted to a request initiator, so that the action sequence and the multi-sensor simulation data are generated. And decomposing the simulated data set by the request initiator, and replacing local sensor interface data by using a Hook method, thereby finally achieving the effect of complete anonymization on the multiple sensors of the mobile equipment.

Description

technical field [0001] The invention belongs to the technical field of information data security, and in particular relates to a sensor data protection method, system, computer equipment and intelligent terminal. Background technique [0002] With the development of the mobile Internet, the integration of new technologies such as smart terminals and location services has spawned unprecedented development of mobile applications and services. Sensors embedded in personal smart devices bring users a convenient experience in customized mobile applications. Like accelerometers, gyroscopes, and magnetometers, the data produced can be used to monitor the user's physical activity, interactions, and emotions. Apps installed on wearable devices can obtain raw sensor data to make inferences for tasks such as gesture recognition or activity recognition. Existing research shows that motion sensors can be used as a medium for side-channel attacks to steal sensitive user input, obtain us...

AI Technical Summary

Problems solved by technology

[0006] (1) The current defense strategies all provide false random data or distorted data such as resampling to the application program, which will inevitably reduce the precision and accuracy of its usability identification, so that the provided data and the real data have a large gap difference, and the false random data is easy to be identified by the service provider, which may cause the crash of the application

Moreover, the current defense strategies are all carried out on the premise of ensuring usability, without considering the privacy protection of the whole life cycle. If the user also needs to protect user background knowledge such as motion information, the current defense strategy cannot effectively protect

[0007] (2) The current simulation data generation method is limited to the use of generative confrontation network to solve the generation problem, and cannot effectively solve the problem of small generated data space; when the number of iterations reaches a certain number, simulation data with high similarity will appear

Moreover, the current simulation data generation method only targets a single sensor when generating data. When the application requires multi-sensor joint judgment, the coordination of multiple sensors cannot be completed, resulting in distortion of the simulation data of the target behavior.

[0008] (3) The existing technology does not consider complete anonymity. When the attacker obtains certain background knowledge, it will affect the protection of user privacy to a certain extent

Images