Ke Xu

Ke Xu

Auto-generated profile, based on publicly available information

Ke Xu

Tsinghua University, Beijing, China

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 January 2021 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
MSMeng Shen
Meng Shen
JZJinpeng Zhang
Jinpeng Zhang
Liehuang ZhuLiehuang Zhu
Liehuang Zhu
KXKe Xu
Ke Xu
Xiaojiang DuXiaojiang Du
Xiaojiang Du
Decentralized Applications (DApps) are increasingly developed and deployed on blockchain platforms such as Ethereum. DApp fingerprinting can identify users' visits to specific DApps by analyzing the resulting network traffic, revealing much sensitive information about the users, such as their real identities, financial conditions and religious or political preferences. DApps deployed on the same platform usually adopt the same communication interface and similar traffic encryption settings, making the resulting traffic less discriminative. Existing encrypted traffic classification methods either require hand-crafted and fine-tuning features or suffer from low accuracy. It remains a challenging task to conduct DApp fingerprinting in an accurate and efficient way. In this paper, we present GraphDApp, a novel DApp fingerprinting method using Graph Neural Networks (GNNs). We propose a graph structure named Traffic Interaction Graph (TIG) as an information-rich representation of encrypted DApp flows, which implicitly reserves multiple dimensional features in bidirectional client-server interactions. Using TIG, we turn DApp fingerprinting into a graph classification problem and design a powerful GNN-based classifier. We collect real-world traffic datasets from 1,300 DApps with more than 169,000 flows. The experimental results show that GraphDApp is superior to the other state-of-the-art methods in terms of classification accuracy in both closed- and open-world scenarios. In addition, GraphDApp maintains its high accuracy when being applied to the traditional mobile application classification.

20 September 2022 in IEEE Communications Surveys & Tutorials
Verified
Journal Article
Closed access
MSMeng Shen
Meng Shen
KYKe Ye
Ke Ye
XLXingtong Liu
Xingtong Liu
Liehuang ZhuLiehuang Zhu
Liehuang Zhu
JKJiawen Kang
Jiawen Kang
KXKe Xu
Ke Xu
Traffic analysis is the process of monitoring network activities, discovering specific patterns, and gleaning valuable information from network traffic. It can be applied in various fields such as network assert probing and anomaly detection. With the advent of network traffic encryption, however, traffic analysis becomes an arduous task. Due to the invisibility of packet payload, traditional traffic analysis methods relying on capturing valuable information from plaintext payload are likely to lose efficacy. Machine learning has been emerging as a powerful tool to extract informative features without getting access to payload, and thus is widely employed in encrypted traffic analysis. In this paper, we present a comprehensive survey on recent achievements in machine learning-powered encrypted traffic analysis. To begin with, we review the literature in this area and summarize the analysis goals that serve as the basis for literature classification. Then, we abstract the workflow of encrypted traffic analysis with machine learning tools, including traffic collection, traffic representation, traffic analysis method, and performance evaluation. For the surveyed studies, the requirements of classification granularity and information timeliness may vary a lot for different analysis goals. Hence, in terms of the goal of traffic analysis, we present a comprehensive review on existing studies according to four categories: network asset identification, network characterization, privacy leakage detection, and anomaly detection. Finally, we discuss the challenges and directions for future research on encrypted traffic analysis.

25 July 2019 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
LCLaizhong Cui
Laizhong Cui
SYShu Yang
Shu Yang
ZCZiteng Chen
Ziteng Chen
YPYi Pan
Yi Pan
MXMingwei Xu
Mingwei Xu
KXKe Xu
Ke Xu
Industrial Internet of Things (IIoT) has been widely used in many fields. Meanwhile, blockchain is considered promising to address the issues of IIoT. However, the current blockchains have limited throughput. In this paper, we devise an efficient and secure blockchain protocol CoDAG based on compacted Directed Acyclic Graph (DAG), where blocks are organized in levels and width. New-generated blocks in CoDAG will be placed appropriately, and point to those in the previous level, making it a well connected channel. Transactions in the network will be confirmed in a deterministic period, and CoDAG keeps a simple data structure at the same time. We also illustrate the attack strategies by adversary, and it is proved that our protocols are resistant to these attacks. Furthermore, we design a CoDAG-based IIoT architecture to improve the efficiency of IIoT system. Experimental results show that CoDAG achieves 164x Bitcoin's throughput and 77x Ethererum's throughput respectively.

8 August 2022 in IEEE/ACM Transactions on Networking
Verified
Journal Article
Closed access
CFChuanpu Fu
Chuanpu Fu
QLQi Li
Qi Li
MSMeng Shen
Meng Shen
KXKe Xu
Ke Xu
Machine learning (ML) based malicious traffic detection is an emerging security paradigm, particularly for zero-day attack detection, which is complementary to existing rule based detection. However, the existing ML based detection achieves low detection accuracy and low throughput incurred by inefficient traffic features extraction. Thus, they cannot detect attacks in realtime, especially in high throughput networks. Particularly, these detection systems similar to the existing rule based detection can be easily evaded by sophisticated attacks. To this end, we propose, a realtime ML based malicious traffic detection system that achieves both high accuracy and high throughput by utilizing frequency domain features. It utilizes sequential information represented by the frequency domain features to achieve bounded information loss, which ensures high detection accuracy, and meanwhile constrains the scale of features to achieve high detection throughput. In particular, attackers cannot easily interfere with the frequency domain features and thus is robust against various evasion attacks. Our experiments with 74 types of attacks demonstrate that, compared with the state-of-the-art systems, can accurately detect various sophisticated and stealthy attacks, achieving at most 18.36% improvement of AUC, while achieving two orders of magnitude throughput. Even under various evasion attacks, is still able to maintain around 90% detection accuracy.

3 December 2019 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
MSMeng Shen
Meng Shen
JZJie Zhang
Jie Zhang
Liehuang ZhuLiehuang Zhu
Liehuang Zhu
KXKe Xu
Ke Xu
Xiangyun TangXiangyun Tang
Xiangyun Tang
Machine learning (ML) techniques are expected to be used for specific applications in Vehicular Social Networks (VSNs). Support vector machine (SVM) is one of the typical ML methods and widely used for its high efficiency. Due to the limitation of data sources, the data collected by different entities usually contain attributes that are quite different. However, in some real-world scenarios, when training an SVM classifier, many entities face the same problem that they are lacking in data with adequate attributes. Thus multiple entities are required to share data to combine a dataset with diverse attributes and then jointly train a comprehensive classifier. However, data privacy concerns are raised because of data sharing. To sovle the problem, we propose a privacy-preserving SVM classifier training scheme over vertically-partitioned datasets posessed by multiple data providers. In our scheme, we utilize consortium blockchain and threshold homomorphic cryptosystem to establish a secure SVM classifier training platform without a trusted third-party. We keep lots of training operations locally over original data and necessary interactions between participants are protected by the threshold Paillier and consortium blockchain. Security analysis proves that our scheme can preserve the privacy of the original data and the training intermediate values. Extensive experiments indicate that our scheme has high efficiency and no accuracy loss.

20 September 2018 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
MSMeng Shen
Meng Shen
BMBaoli Ma
Baoli Ma
Liehuang ZhuLiehuang Zhu
Liehuang Zhu
Xiaojiang DuXiaojiang Du
Xiaojiang Du
KXKe Xu
Ke Xu
Phrase search allows retrieval of documents containing an exact phrase, which plays an important role in many machine learning applications for cloud-based IoT, such as intelligent medical data analytics. In order to protect sensitive information from being leaked by service providers, documents (e.g., clinic records) are usually encrypted by data owners before being outsourced to the cloud. This, however, makes the search operation an extremely challenging task. Existing searchable encryption schemes for multi-keyword search operations fail to perform phrase search, as they are unable to determine the location relationship of multiple keywords in a queried phrase over encrypted data on the cloud server side. In this paper, we propose P3, an efficient privacy-preserving phrase search scheme for intelligent encrypted data processing in cloud-based IoT. Our scheme exploits the homomorphic encryption and bilinear map to determine the location relationship of multiple queried keywords over encrypted data. It also utilizes a probabilistic trapdoor generation algorithm to protect users’ search patterns. Thorough security analysis demonstrates the security guarantees achieved by P3. We implement a prototype and conduct extensive experiments on real-world datasets. The evaluation results show that compared with existing multi-keyword search schemes, P3 can greatly improve the search accuracy with moderate overheads.