Zhejiang University

Wenyuan Xu

Yanjiao Chen

Xiaoyu Ji

Xu Wang

Yonggang Peng

Siheng Chen

Kai Huang

Wenjun Zhu

Xiaoxu Zhang

Chen Yan

Zhili Liu

Xiaowen Jiang

Qianhao Miao

Tianchen Zhang

Jiahan Dong

Yushi Cheng

Guoming Zhang

Nige Li

Taimin Zhang

Yinan Zhong

A camera with a privacy protection function and a camera privacy protection method therefor are provided, which relates to the field of image privacy protection. The camera includes an image acquisition module, a parameter storage module, an access control module, and an image post-processing module. An objective of the privacy protection method of the camera is to enable an image shot by the camera to naturally have a privacy protection capability to resist sniffing of a malicious third party to personal privacy, which includes, but is not limited to, face recognition. A system deeply participates in a generation process of an image from a plurality of levels, which can affect various procedures including image signal processing, image color adjustment, and an image encoding process, and provide a platform for the development and application of underlying privacy protection algorithms.

Camera with privacy protection function and privacy protection method

The present invention relates to the technical field of central processing units (CPUs), and in particular to a fault-tolerant system with multi-core CPUs capable of being dynamically configured. The multi-core CPUs are three reconfigurable CPUs, the fault-tolerant system with multi-core CPUs is statically configured to be in a normal fault-tolerant mode, a reliable fault-tolerant mode or a performance mode by means of configuration of the three CPUs and then is switched between the normal fault-tolerant mode, the reliable fault-tolerant mode and the performance mode according to a mode switching command of a mode switching register, and finally, the three CPUs are correspondingly configured according to the mode to be switched.

Fault-tolerant system with multi-core CPUs capable of being dynamically configured

A secure and trusted three-party device fingerprint authentication method is disclosed. The method includes the following steps: S1. authentication preparation stage: dividing subjects involved in fingerprint authentication into a device party U, a service party P and a storage party V, uploading and verifying an execution program of a trusted execution environment TEE; S2. authentication initialization stage: establishing the trusted execution environment TEE by the service party P, and establishing a security channel between the trusted execution environment TEE, the device party U and the storage party V; and S3. device fingerprint authentication stage: uploading a fingerprint and a fingerprint library to the trusted execution environment TEE through the security channel by the device party U and the storage party V, respectively, after completing a device fingerprint authentication, obtaining an authentication result through the security channel.

Secure and trusted three-party device fingerprint authentication method

A covert channel construction method in a blockchain network includes: sharing, by a first terminal and a second terminal, a secret key and transaction information, and generating a blockchain network address by using the secret key and a standard public key address generation algorithm, wherein the transaction information comprises a permutation mapping table and an information capacity of a single transaction; sending, by the first terminal, information by using an information hiding method, and performing simultaneously, by the first terminal and the second terminal, transaction recording; and monitoring, by the first terminal and the second terminal, whether an account transaction of the blockchain network address exists in a blockchain, if yes, extracting, by the second terminal, the information by using an information extraction method, and after extracting the information, replying to the information by using the information hiding method, thereby enabling communication parties to safely transmit information.

Covert channel construction method in blockchain network

The present disclosure discloses a machine learning-based method for defending a voice assistant from being controlled by an inaudible command, including following steps: 1) collecting data of positive and negative samples, 2) performing data segmentation on data of the positive and negative samples; 3) selecting and normalizing sample features; 4) selecting a classifier to be trained and generate a detection model for a malicious voice command; 5) detecting a voice command to be detected by the detection model. The present disclosure selects an original feature selection method, and for smart devices of different types, it is necessary to obtain normal voice commands and malicious voice commands by means of a smart device of this type, and use them as the positive and negative samples to train a specific classifier for the device. Such a customized approach can well solve a problem that detection and defense between devices cannot work.

Method of defending against inaudible attacks on voice assistant based on machine learning

Growing community of inventors

Hangzhou, China

Wenyuan Xu