Search

Website fingerprinting attack is an effective way to infer which web page a user is browsing through anonymous network. Previous studies focused more on the selection of traffic features and improvements in traditional classification methods. In this paper, we present a new website fingerprinting technique based on deep learning. The method uses a complex deep neural network to automatically learn features and classify website fingerprints. The model uses two-layer GRU network to extract the time feature and the 50-layer residual network to extract the spatial features of the website fingerprint. The main idea resides in the fact that deep neural network can achieve complex function approximation and more efficient feature extraction. Our technique performs better than the current state-of-the-art website fingerprint attack. We have achieved more than 99% accuracy over the current largest dataset which consists of 900 classes. The results of experiment show that deep learning is an efficient and robust technique for website fingerprint attack.

It is an important task in network security management to use defensive strategy to mitigate security risk. We obtain the Pareto-optimal set of defensive strategy using multi-objective optimization algorithm (MOO) based on attack tree. However, decision maker (DM) may find it problematic to select an appropriate defensive strategy from the Pareto-optimal set, and visualization of the Pareto-optimal set is an effective method. In well-known spectral seriation of heatmap, there exist problem of mapping identical objective values of the Pareto-optimal set to different colors. And there still exist problem of weak flexibility and interactivity while the original spectral seriation of heatmap doesn't provide interface for DM. We improve the clarity by mapping identical objective values to the same color through assigning identical ranked values for identical objective values, and increase interactivity by allowing DM reorder objects and solutions or set interested solutions. Finally, the most suitable defensive strategy will be obtained from the improved heatmap easily. Application and advantages of the proposed approach are illustrated through a case study.

With the development of internet, the network connection between Industrial Control System (ICS) and public internet has been becoming more and more closely. What's more, the traditional IT system attacks have been spread to ICS and become more frequently. However, the traditional security analysis of IT system is not enough to be applied to ICS. In this paper, we present a tool called Attack Path Modeling and Analysis System (APMAS), which provides a graphical user interface (GUI) for the user to model and analyze ICS attack interaction. The main four components including network modeling, rule modeling, attack tree modeling and security analysis are briefly described. Moreover, we propose a solution combined with multi-objective optimization to generate a Pareto front consisting of a group of defense suggestions.