The act of website fingerprinting, which involves monitoring traffic features to infer private user information, has attracted much attention in the research community recently. While previous studies primarily focused on classifying fingerprint information using clean traffic data, it remains a challenging task to apply fingerprinting to noisy traffic data or evade defensive measures. This work aims to address the challenges associated with website fingerprinting attacks and defense strategies in the presence of noise. Specifically, we introduce two novel attack methods: filter-assisted attack and augmentation-assisted attack. The first attack method leverages packet size distribution to effectively filter out noise, while the second one trains a classification model by incorporating artificial noise. Compared with the traditional website fingerprinting attacks, these proposed attack methods demonstrate superior resilience to noise and exceptional evasion capabilities against defensive measures (e.g., random packet defense, Walkie-Talkie, WTF-PAD, etc.). In parallel, we propose a list-assisted defense strategy that strikes a balance between defense performance and network overhead. This defense mechanism offers effective protection against website fingerprinting attacks while minimizing the impact on network performance. In our experiments, we employ a comprehensive dataset encompassing TCP/IP traffic with packet size information collected from three prominent web browsers, as well as Tor cell traffic without packet size information obtained from a Tor browser. We thoroughly evaluate our proposed methods in both closed-world and open-world scenarios. Our experimental results shed valuable insights into the influence of noise and the efficacy of different attack and defense approaches on website fingerprinting.

Website fingerprinting attack is an extensively studied technique used in a web browser to analyze traffic patterns and thus infer confidential information about users. Several website fingerprinting attacks based on machine learning and deep learning tend to use the most typical features to achieve a satisfactory performance of attacking rate. However, these attacks suffer from several practical implementation factors, such as a skillfully pre-processing step or a clean dataset. To defend against such attacks, random packet defense (RPD) with a high cost of excessive network overhead is usually applied. In this work, we first propose a practical filter-assisted attack against RPD, which can filter out the injected noises using the statistical characteristics of TCP/IP traffic. Then, we propose a list-assisted defensive mechanism to defend the proposed attack method. To achieve a configurable trade-off between the defense and the network overhead, we further improve the list-based defense by a traffic splitting mechanism, which can combat the mentioned attacks as well as save a considerable amount of network overhead. In the experiments, we collect real-life traffic patterns using three mainstream browsers, i.e., Microsoft Edge, Google Chrome, and Mozilla Firefox, and extensive results conducted on the closed and open-world datasets show the effectiveness of the proposed algorithms in terms of defense accuracy and network efficiency.

Model transformations are touted to play a key role in model-driven software development. The mapping relations between different models are the foundation and basis for the transformation. A classification for different level mappings was proposed and defined formally by abstractly analyzing the characteristics of syntax and semantic features of modeling languages. On this basis, a further study about the simulation-based mapping approach was conducted to explore the definition process for mapping relations and the cardinal principles should be followed. The UML-based class model used as a source and the C programming language used as the target are shown in the case study to help interpreting the ideas. It may not only be a theoretical guidance for model transformation, but also can be a measurement for validating the mapping rules between models at different abstract levels.

The transformation from platform independent models to platform specific models is a key technology in OMG's MDA. The mapping relations between different models are the foundation and basis for the transformation. By abstractly analyzing the characteristic of syntax and semantics of modeling languages, a semantic-features-calculation based model mapping approach for the development of Web information systems was proposed. To using this approach, abstract target semantic model should be constructed firstly. Then, based on the idea of elements in source semantic domain being reconstructed in the target semantic domain, mapping relations from source model to target model are made via abstract target semantic model. This approach may not only to be a theoretical guidance for model transformation, but also can be a measurement for validating the mapping rules between models at different abstract levels. JavaServer Faces assisted with Enterprise JavaBeans was used as a target platform to help interpreting the process of using this approach.

In the traditional B-method, operations are designed only by pre-conditions and a series of substitutions, and it works well. However, with the appearance and development of the modeling by the integration of semi-formal methods (especially UML) and formal methods, the condition changes. Without the formal notations interrelated to the post-condition, B-method cannot be embedded into UML models conveniently and flexibly in order to exert all its powers to describe systems exactly. This conditions indeed limit the adoption of B, and it is really necessary to extend the correlative definitions and properties. Therefore, this paper proposes the PostB, the extension referred to the formal notations of the post-condition to the B method, as well as the extended set-theorem models and proof obligations referred to it.