Hanbing Yan

Hanbing Yan

Auto-generated profile, based on publicly available information

Hanbing Yan

National Computer Network Emergency Response Technical Team/Coordination Center of China (CNCERT/CC)

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
20 November 2018 in IEEE Access
Verified
Journal Article
Open access
HZHua Zhang
Hua Zhang
HGHongchao Guan
Hongchao Guan
HYHanbing Yan
Hanbing Yan
WLWenmin Li
Wenmin Li
YYYuqi Yu
Yuqi Yu
XZXingyu Zeng
Xingyu Zeng
Webshell is a kind of backdoor programs based on web services. Network based detection could monitor the request and response traffic to find abnormal behaviors and detect the existence of Webshell. Some machine learning and deep learning methods have been used in this field, but the current methods need to be further explored in discovering new attacks and performance. In order to detect large-scale unknown Webshell events, we propose a Webshell traffic detection model combining the characteristics of convolutional neural network (CNN) and long short term memory network (LSTM). At the same time, we propose a character level traffic content feature transformation method. We apply the method in our proposed model and evaluate our approach on a Webshell detection testbed. The experiment result indicates that the model has a high precision rate and recall rate, and the generalization ability can be guaranteed.

20 February 2019
Verified
Book Chapter
Open access
PDF file
ZLZhuo-Hang Lv
Zhuo-Hang Lv
HYHan-Bing Yan
Han-Bing Yan
RMRui Mei
Rui Mei
The rapid development of the Internet has changed the way people live and work. Web security, as the foundation of network security, has received much more attention. Based on the variability of Webshells and the vulnerability of detection methods, this paper proposed a model that used deep learning to detect and implements the automatic identification of Webshells. For the shortcomings of the traditional detection models using machine learning algorithms, this paper proposed to apply convolutional neural network to Webshell detection process. The deep learning model does not require complicated artificial feature engineering, and the modeled features trained through model learning can also allow the attacker to avoid targeted bypassing in Webshell detection. The experimental results showed that this method not only has better detection accuracy, but also can effectively avoid the attacker’s targeted bypassing. At the same time, with the accumulation of training samples, the detection accuracies of the detection model in different application environments will gradually improvements, which has clear advantages over traditional machine learning algorithms.

10 December 2022
Verified
Book Chapter
Open access
PDF file
RMRui Mei
Rui Mei
HYHan-Bing Yan
Han-Bing Yan
YHYongqiang He
Yongqiang He
QWQinqin Wang
Qinqin Wang
SZShengqiang Zhu
Shengqiang Zhu
WWWeiping Wen
Weiping Wen
With the continuous growth of enterprises’ digital transformation, business-driven cloud computing has seen tremendous growth. The security community has proposed a large body of technical mechanisms, operational processes, and practical solutions to achieve cloud security. In addition, diverse jurisdictions also present regulatory requirements on data protection to mitigate possible risks, for instance, unauthorized access, data leakage, sensitive information and privacy disclosure. In view of this, several practical standards, frameworks, and best practices in the industry are proposed to evaluate and improve the protection level of cloud data. However, few evaluation models can conduct a comprehensive quantitative evaluation for cloud data protection that includes security, privacy, and even ethical considerations. In this paper, we first make a comprehensive review of cloud data security and privacy issues, especially also including ethical concerns that we consider as a type of specific risks caused by human factors, which refers to acting honorably, honestly, justly, and legally, due diligence, and due care. Then, we propose a novel evaluation model for cloud data protection that can quantitatively assess the protection level. Finally, based on the parallel evaluation between manual assessment by experts and our evaluation model, results show that our evaluation model is consistent with the manual evaluation conclusion.

9 November 2020 in Wireless Personal Communications
Verified
Journal Article
Closed access
PDF file
HLHao Lin
Hao Lin
HZHua Zhang
Hua Zhang
HYHanbing Yan
Hanbing Yan
HWHuawei Wang
Huawei Wang
YSYijie Shi
Yijie Shi
QWQiaoyan Wen
Qiaoyan Wen

1 January 2020
Verified
Book Chapter
Open access
PDF file
YYYuqi Yu
Yuqi Yu
HYHanbing Yan
Hanbing Yan
YMYuan Ma
Yuan Ma
HZHao Zhou
Hao Zhou
HGHongchao Guan
Hongchao Guan
Hypertext Transfer Protocol (HTTP) accounts for a large portion of Internet application-layer traffic. Since the payload of HTTP traffic can record website status and user request information, many studies use HTTP protocol traffic for web application attack detection. In this work, we propose DeepHTTP, an HTTP traffic detection framework based on deep learning. Unlike previous studies, this framework not only performs malicious traffic detection but also uses the deep learning model to mine malicious fields of the traffic payload. The detection model is called AT-Bi-LSTM, which is based on Bidirectional Long Short-Term Memory (Bi-LSTM) with attention mechanism. The attention mechanism can improve the discriminative ability and make the result interpretable. To enhance the generalization ability of the model, this paper proposes a novel feature extraction method. Experiments show that DeepHTTP has an excellent performance in malicious traffic discrimination and pattern mining.

9 October 2018 in IEEE Access
Verified
Journal Article
Open access
WYWei Yin
Wei Yin
QWQiaoyan Wen
Qiaoyan Wen
KLKaitai Liang
Kaitai Liang
ZZZhenfei Zhang
Zhenfei Zhang
LCLiqun Chen
Liqun Chen
HZHua Zhang
Hua Zhang
The notion of decryption rights delegation was initially introduced by Blaze et al. in EUROCRYPT 1998. It, defined as proxy re-encryption, allows a semi-trusted proxy to convert a ciphertext intended for a party to another ciphertext of the same plaintext, without knowledge of the underlying plaintext and decryption key. It has been explored to many real-world applications, e.g., encrypted email forwarding. However, the intrinsic all-or-nothing share feature of proxy re-encryption yields a limitation that the share cannot be revoked. This may hinder the scalability of its applications in practice. In this paper, for the first time, we define the concept of revocability in terms of decryption rights delegation. The novel concept enables data owner to revoke the shared decryption rights when needed. Inspired by the seminal lattice-based proxy re-encryption proposed in PKC 2014, we design a concrete lattice-based construction which satisfies the notion. In our construction, we make use of binary-tree structure to implement the revocation of decryption rights, so that the update of re-encryption key is reduced to O(logN) (instead of O(N)), where N is the maximum number of delegatee. Furthermore, the security of our scheme is based on the standard learning with errors problem(LWE problem), which could be reduced to the worst-case hard problems (such as GapSVP and SIVP) in the context of lattices. The scheme is chosen ciphertext secure in the standard model. As of independent interest, our scheme achieves both backward and forward security, which means that once a user is revoked after a time period t, it cannot gain access to all encrypted files before and after t.