Illegal elements use the characteristics of an anonymous network hidden service mechanism to build a dark network and conduct various illegal activities, which brings a serious challenge to network security. The existing anonymous traffic classification methods suffer from cumbersome feature selection and difficult feature information extraction, resulting in low accuracy of classification. To solve this problem, a classification method based on three-dimensional Markov images and output self-attention convolutional neural network is proposed. This method first divides and cleans anonymous traffic data packets according to sessions, then converts the cleaned traffic data into three-dimensional Markov images according to the transition probability matrix of bytes, and finally inputs the images to the output self-attention convolution neural network to train the model and perform classification. The experimental results show that the classification accuracy and F1-score of the proposed method for Tor, I2P, Freenet, and ZeroNet can exceed 98.5%, and the average classification accuracy and F1-score for 8 kinds of user behaviors of each type of anonymous traffic can reach 93.7%. The proposed method significantly improves the classification effect of anonymous traffic compared with the existing methods.

A film stress measurement system applicable for hyperbaric environment was developed to characterize stress evolution in a physical simulation test of a gas-solid coupling geological disaster. It consists of flexible film pressure sensors, a signal conversion module, and a highly-integrated acquisition box which can perform synchronous and rapid acquisition of 1 kHz test data. Meanwhile, we adopted a feasible sealing technology and protection method to improve the survival rate of the sensors and the success rate of the test, which can ensure the accuracy of the test results. The stress measurement system performed well in a large-scale simulation test of coal and gas outburst that reproduced the outburst in the laboratory. The stress evolution of surrounding rock in front of the heading is completely recorded in a successful simulation of the outburst which is consistent with the previous empirical and theoretical analysis. The experiment verifies the feasibility of the stress measurement system as well as the sealing technology, laying a foundation for the physical simulation test of gas-solid coupled geological disasters.