Yaojun Hao

Yaojun Hao

Auto-generated profile, based on publicly available information

Yaojun Hao

School of Information Science and Engineering, Yanshan University, Qinhuangdao, China

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

5 December 2022 in Information Systems
Verified
Journal Article
Closed access
YHYaojun Hao
Yaojun Hao
GMGuoyan Meng
Guoyan Meng
JWJian Wang
Jian Wang
CZChunmei Zong
Chunmei Zong

5 August 2019 in Security and Communication Networks
Verified
Journal Article
Open access
PDF file
YHYaojun Hao
Yaojun Hao
FZFuzhi Zhang
Fuzhi Zhang
JWJian Wang
Jian Wang
QZQingshan Zhao
Qingshan Zhao
JCJianfang Cao
Jianfang Cao
Due to the openness of the recommender systems, the attackers are likely to inject a large number of fake profiles to bias the prediction of such systems. The traditional detection methods mainly rely on the artificial features, which are often extracted from one kind of user-generated information. In these methods, fine-grained interactions between users and items cannot be captured comprehensively, leading to the degradation of detection accuracy under various types of attacks. In this paper, we propose an ensemble detection method based on the automatic features extracted from multiple views. Firstly, to collaboratively discover the shilling profiles, the users’ behaviors are analyzed from multiple views including ratings, item popularity, and user-user graph. Secondly, based on the data preprocessed from multiple views, the stacked denoising autoencoders are used to automatically extract user features with different corruption rates. Moreover, the features extracted from multiple views are effectively combined based on principal component analysis. Finally, according to the features extracted with different corruption rates, the weak classifiers are generated and then integrated to detect attacks. The experimental results on the MovieLens, Netflix, and Amazon datasets indicate that the proposed method can effectively detect various attacks.

11 October 2018 in Security and Communication Networks
Verified
Journal Article
Open access
PDF file
YHYaojun Hao
Yaojun Hao
PZPeng Zhang
Peng Zhang
FZFuzhi Zhang
Fuzhi Zhang
Faced with the evolving attacks in collaborative recommender systems, the conventional shilling detection methods rely mainly on one kind of user-generated information (i.e., single view) such as rating values, rating time, and item popularity. However, these methods often suffer from poor precision when detecting different attacks due to ignoring other potentially relevant information. To address this limitation, in this paper we propose a multiview ensemble method to detect shilling attacks in collaborative recommender systems. Firstly, we extract 17 user features by considering the temporal effects of item popularity and rating values in different popular item sets. Secondly, we devise a multiview ensemble detection framework by integrating base classifiers from different classification views. Particularly, we use a feature set partition algorithm to divide the features into several subsets to construct multiple optimal classification views. We introduce a repartition strategy to increase the diversity of views and reduce the influence of feature order. Finally, the experimental results on the Netflix and Amazon review datasets indicate that the proposed method has better performance than benchmark methods when detecting various synthetic attacks and real-world attacks.

5 June 2024 in Information Systems
Verified
Journal Article
Closed access
YHYaojun Hao
Yaojun Hao
HWHaotian Wang
Haotian Wang
QZQingshan Zhao
Qingshan Zhao
LFLiping Feng
Liping Feng
JWJian Wang
Jian Wang

1 January 2026 in IET Information Security
Verified
Journal Article
Open access
NHNingyu Hu
Ningyu Hu
YHYaojun Hao
Yaojun Hao
Blockchain organizes information through a chain structure, and retrieving data from the blockchain requires traversing blocks. This makes traditional retrieval methods unsuitable for intensive query scenarios. To address the inefficiency of blockchain data retrieval, this paper proposes an efficient and secure retrieval method based on Merkle Patricia tries (MPTs). The method uses users’ public keys to construct a global latest state index tree, enabling quick access to the latest transaction information of a queried user as both sender and receiver. The hash of the latest state index tree is stored in the block header to ensure the verifiability and immutability of the index information. Additionally, the transaction structure in the block is reconstructed to include the hash and block height of the previous transaction for the same user. This allows simultaneous retrieval of the current and previous transaction information, improving retrieval speed. Experiments demonstrate that the proposed method significantly enhances retrieval efficiency within acceptable construction costs. Furthermore, the more transaction versions traced back, the greater the advantage of the method.