Research On Detection Technology Based On Dynamic Browser Fingerprint

With the emergence of user privacy leakage and online fraud,traditional detection mechanisms can no longer stop the intensified attacks,and new technical methods are needed to assist in Web security detection.As a bridge between users and network data,browsers are widely used in the interaction between users and various applications.The browser fingerprint contains various characteristic information such as the user's browser and device,and its uniqueness can greatly improve the accuracy of user identification.However,browser fingerprints will continue to change over time,and research solutions based on static fingerprints cannot meet the requirements of dynamic fingerprints detection.In response to this problem,this paper aims to improve the recognition and link detection capabilities of dynamic browser fingerprints.The main research work is as follows:(1)To solve the problem that browser fingerprint features are not selected comprehensively and only focus on a single attribute such as WebGL or Canvas,this paper obtains parameters from multi-dimensional perspective and screen them to get fine-grained and high-discrimination features for model detecting.At the same time,in order to track the ever-changing browser fingerprint as much as possible,let the fingerprint information of the same user can be linked to the corresponding fingerprint chain,this paper proposes a stacked BiGRU detection model based on dynamic browser fingerprints.Which solves the problem of low detection accuracy caused by ignoring the interaction of forward and backward information in the process of fingerprints detection,and has a certain improvement in comprehensive indicators such as accuracy and linking time.(2)In view of the different importance of different feature parameters,features with high information entropy have a greater influence in the detection process,and the same weight given to parameters will result in detection error.This paper proposes an Att-BiGRU fingerprint detection model based on dynamic browser fingerprints,and combined with the attention mechanism to focus more stable fingerprint features.It has a performance optimization compared to BiGRU,and shows good linking capabilities in the experimental results.(3)In response to malicious attacks on browser fingerprints,the attacker can forge user fingerprints to steal privacy information,this paper first extracts abnormal data and expands it to form a new test data set.The benchmark model and the model proposed in this paper are tested by using the new data set.The robustness of the proposed model is verified by the comparative analysis of the experimental results,and it has stronger anti-attack ability than the existing models.