A privacy protection face recognition system and method for smart home

Abstract

The invention discloses a privacy protection face recognition system and method for smart home, including a user end, a home terminal device, and an authentication server; extracting face feature data, generating and storing encryption keys required for face recognition The feature data is encrypted and saved, and when the user logs in for recognition, the encrypted face feature data is received, then compared and calculated, and the recognition result is returned to the home terminal device. Compared with the prior art, the present invention realizes the privacy protection of data resources; can resist various network attack methods; ensures the local security of the key, making it more difficult for attackers to destroy; Space complexity is minimized.

Description

technical field [0001] The invention belongs to the technical field of information security, and in particular relates to a smart home-oriented privacy protection face recognition method and system, and a mobile terminal. Background technique [0002] With the further development of wireless communication and intelligent perception, the Internet of Things technology has received widespread attention and development. Smart home is the embodiment of the connection of the home environment under the influence of the Internet of Things. Smart home connects various devices in the home (access control system, access control system, audio and video equipment, lighting system, curtain control, air conditioning control, security system, network appliances, etc.) , Curtain control, telephone remote control, indoor and outdoor remote control, anti-theft alarm, environmental monitoring, HVAC control, infrared forwarding and programmable timing control and other functions and means. How...

AI Technical Summary

Problems solved by technology

However, due to the lack of consideration of the designer in this method, there is a problem that the face model is not encrypted and the privacy of user data is not protected.

Once the face model is stolen, not only the user's privacy will be leaked, but the attacker can also pretend to be the user for authentication, which will cause great harm

[0003] To sum up, the problems existing in the existing technology are: the existing face recognition method cannot take into account the recognition accuracy, communication overhead and time overhead, and the user data is not encrypted; in the application, the user's privacy will be leaked, and it is easy to be Forged face attack and high error rate or high communication overhead

[0004] The difficulty and significance of solving the above technical problems: traditional face recognition technology does not have an encryption module, once the system is attacked, it is easy to leak user privacy, and at the same time, the attacker can pretend to be the user for identification, which greatly increases the system risk

Homomorphic encryption technology will bring large communication overhead and computing time, and the hardware conditions of IoT terminal devices cannot support such a huge overhead

At the same time, recoverable symmetric encryption cannot be used, because sensitive data will be exposed to the server

Therefore, it is necessary to find a new and efficient privacy protection encryption method for face recognition in the smart home environment, which can realize the protection of user privacy data without affecting the efficiency and accuracy of face recognition, and even if the data is stolen, it cannot be used.

Images