The subpath kernel is a class of positive definite kernels defined over trees, which has the following advantages for the purposes of classification, regression and clustering: it can be incorporated into a variety of powerful kernel machines including SVM; It is invariant whether input trees are ordered or unordered; It can be computed by significantly fast linear-time algorithms; And, finally, its excellent learning performance has been proven through intensive experiments in the literature. In this paper, we leverage recent advances in tree kernels to solve real problems. As an example, we apply our method to the problem of detecting fake e-commerce sites. Although the problem is similar to phishing site detection, the fact that mimicking existing authentic sites is harmful for fake e-commerce sites marks a clear difference between these two problems. We focus on fake e-commerce site detection for three reasons: e-commerce fraud is a real problem that companies and law enforcement have been cooperating to solve; Inefficiency hampers existing approaches because datasets tend to be large, while subpath kernel learning overcomes these performance challenges; And we offer increased resiliency against attempts to subvert existing detection methods through incorporating robust features that adversaries cannot change: the DOM-trees of web-sites. Our real-world results are remarkable: our method has exhibited accuracy as high as 0.998 when training SVM with 1000 instances and evaluating accuracy for almost 7000 independent instances. Its generalization efficiency is also excellent: with only 100 training instances, the accuracy score reached 0.996.

Wang B, et al. J Breast Cancer. 2022 Jun;25(3):193-206. https://doi.org/10.4048/jbc.2022.25.e24

Fake sites are serious threats for both consumers and merchants. They mimic authentic sites and attempt to obtain money by fraud, steal personal information such as credit card numbers from consumers, ruin merchants' reputation and so on. Usually, it is difficult for consumers to distinguish between authentic sites and fake sites. In this paper, we propose a method to detect fake sites with high accuracy based on analyzing structures of HTML source codes of websites. For the analysis, we leverage a combination of a tree kernel and the support vector machine (SVM). We first test 32 different types of tree kernels with small datasets, and then, select a few kernels that have exhibited the best accuracy scores. Further, we test them with larger datasets, and finally, focus on a single kernel that has shown the best accuracy and speed. The AUC, F-measure, Accuracy scores of the kernel exceed 0.97 with a large dataset with 3001 instances, and we conclude that the method can perform at the practical level.

Source-location privacy (SLP) is a critical security property in event-surveillance systems. However, due to the characteristics of surveillance systems, e.g., resource constraints, diverse privacy requirements and large-scale network, the existing anonymity mechanisms cannot effectively deal with the problem of source location privacy protection. This paper proposes the dynamic optimal mix-ring-based source-location anonymity protocol, DORing. In this scheme, we set the optimal mix-ring to collect and mix the network traffic which can satisfy the diverse QoS requirements. The location of mix-ring is adjusted to balance network energy consumption, prolong the lifetime of the network, and resist global attack. The simulation results demonstrate that DORing can significantly prolong survival period of the network and ensure security as well as latency to satisfy the packets' requirements.