Enhuan Dong

Prof. Enhuan Dong

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications

13 August 2024 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
RXRenjie Xie
Renjie Xie
JCJiahao Cao
Jiahao Cao
YZYuxi Zhu
Yuxi Zhu
YZYixiang Zhang
Yixiang Zhang
YHYi He
Yi He
JLJiang Li
Jiang Li
As the mainstream encrypted protocols adopt TCP protocol to ensure lossless data transmissions, the privacy of encrypted TCP traffic becomes a significant focus for adversaries. They can leverage Deep Learning (DL) models to infer the sensitive information from encrypted TCP traffic by analyzing its packet size, direction, and timing information. To defend against such DL-based traffic analysis attacks, recent advances reshape the encrypted traffic and achieve desired results. However, they typically require deploying cooperative modules on both communication endpoints and only support specific applications, such as browsers. In this paper, we propose Cactus, a client-side plug-in to obfuscate bidirectional encrypted TCP traffic for a wide range of applications transparently using the inherent TCP semantics and the emerging eBPF technique. In particular, Cactus provides four effective operations to enable bidirectional traffic obfuscation while preserving communication semantics of applications. Besides, Cactus empowers users to specify which applications to conduct traffic obfuscation and what obfuscation level for each application. We conduct comprehensive experiments to demonstrate that Cactus can effectively obfuscate encrypted TCP traffic with low overhead to hinder the traffic analysis efforts in website fingerprinting and application identification.

22 April 2020 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
Enhuan DongEnhuan Dong
Enhuan Dong
XFXiaoming Fu
Xiaoming Fu
MXMingwei Xu
Mingwei Xu
YYYuan Yang
Yuan Yang
Load balancing in datacenter networks (DCNs) is an important and challenging task for datacenter managers. A number of sophisticated technologies have been proposed to improve load balancing performance in a complicated circumstance, i.e., with various traffic characteristics. Many approaches need a high cost to implement, such as changing switch hardware. The efficiency problem has not been well addressed. MPTCP was proposed as a low-cost approach to improve data transmission in DCNs, which uses subflows to balance workloads across multiple paths. However, current MPTCP is not satisfying, especially when there are rack-local flows or many-to-one short flows. In this paper, we propose DCMPTCP to improve the efficacy of MPTCP. We gradually develop three mechanisms. First, DCMPTCP identifies rack-local traffic and eliminates unnecessary subflows to reduce the overhead. Second, DCMPTCP estimates flow length and establishes subflows in a smarter way. Third, DCMPTCP strengthens explicit congestion notification to improve the congestion control performance on inter-rack many-to-one short flows. We have implemented DCMPTCP in both the Linux kernel and ns-3 simulator. Our comprehensive testbed experiments and simulations show that DCMPTCP outperforms MPTCP in both 1Gbps testbed, and 10Gbps large-scale simulation network.

30 September 2023 in Computer Networks
Verified
Journal Article
Closed access
Enhuan DongEnhuan Dong
Enhuan Dong
PGPeng Gao
Peng Gao
YYYuan Yang
Yuan Yang
MXMingwei Xu
Mingwei Xu
XFXiaoming Fu
Xiaoming Fu
JYJiahai Yang
Jiahai Yang

13 January 2025 in IEEE Journal on Selected Areas in Communications
Verified
Journal Article
Closed access
YLYi Liu
Yi Liu
NGNan Geng
Nan Geng
MXMingwei Xu
Mingwei Xu
YYYuan Yang
Yuan Yang
Enhuan DongEnhuan Dong
Enhuan Dong
JWJianping Wu
Jianping Wu
Traffic engineering (TE) has attracted extensive attention over the years. Operators expect to design a TE scheme that accommodates traffic dynamics well and achieves good TE performance with little overhead. Some approaches like oblivious routing compute an optimal static routing based on a large traffic matrix (TM) range, which usually leads to much performance loss. Many approaches compute routing solutions based on one or a few representative TMs obtained from observed historical TMs. However, they may suffer from performance degradation for unexpected TMs and usually induce much overhead of system operating. In this paper, we propose ALTE, an adaptive and low-cost TE scheme based on TM classification. We develop a novel clustering algorithm to properly group a set of historical TMs into several clusters and compute a candidate routing solution for each TM cluster. A machine learning classifier is trained to infer the proper candidate routing solution online based on the features extracted from some easily measured statistics. We implement a system prototype of ALTE and do extensive simulations and experiments using both real and synthetic traffic traces. The results show that ALTE achieves near-optimal performance for dynamic traffic and introduces little overhead of routing updates.

7 March 2024 in IEEE Network
Verified
Journal Article
Closed access
LQLibing Qiao
Libing Qiao
Enhuan DongEnhuan Dong
Enhuan Dong
HYHuanpu Yin
Huanpu Yin
HLHaisheng LI
Haisheng LI
JYJiahai Yang
Jiahai Yang
With the continuous development of network devices, there are increasingly types and quantities of network devices. Accurate identification of device types helps proactively protect potentially vulnerable devices exposed on the Internet. Among the network device identification methods, the TCP/IP stack active detection method is an important kind since it does not require many open ports of target devices. However, its performance is limited by the rule/fingerprint database quality. Maintaining such a database requires a lot of expert effort, making the method difficult to scale up. To solve the scalability problem, our insight in this paper is to use machine learning methods to generate network device classifiers without needing expert effort. However, generating labeled datasets, extracting features, and selecting features without expert effort is non-trivial. We propose IntelliNDI , an intelligent and active network device identification method. IntelliNDI collects network device type information from multiple cyberspace search engines and filter out the network devices with different types on different search engines. We regard the approximately consistent network device types as the ground truth network device types. As for feature extraction, we use the same attributes employed in the well-known Nmap protocol stack detection to avoid the requirements for constructing features. Finally, we select features with basic ML methods. We implement IntelliNDI for several kinds of typical network devices. The trained classifiers in our experiments can achieve 90 percent accuracy.