Zhihai Yang

Prof. Zhihai Yang


Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
25 July 2016 in Journal of Intelligent Information Systems
Verified
Journal Article
Closed access
PDF file
ZYZhihai Yang
Zhihai Yang
ZCZhongmin Cai
Zhongmin Cai

14 August 2020 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
ZYZhihai Yang
Zhihai Yang
QSQindong Sun
Qindong Sun
YZYaling Zhang
Yaling Zhang
WWWei Wang
Wei Wang
Personalized recommender systems are pervasive in different domains, ranging from e-commerce services, financial transaction systems to social networks. The generated ratings and reviews by users toward products are not only favourable to make targeted improvements on the products for online businesses, but also beneficial for other users to get a more insightful review of the products. In reality, recommender systems can also be deliberately manipulated by malicious users due to their fundamental vulnerabilities and openness. However, improving the detection performance for defending malicious threats including profile injection attacks and co-visitation injection attacks is constrained by the challenging issues: (1) various types of malicious attacks in real-world data coexist; (2) it is difficult to balance the commonality and speciality of rating behaviors in terms of accurate detection; and (3) rating behaviors between attackers and anchor users caused by the consistency of attack intentions are extremely similar. In this paper, we develop a unified detection approach named IMIA-HCRF, to progressively discriminate malicious injection behaviors for recommender systems. First, disturbed data are empirically eliminated by implementing both the construction of association graph and enhancement of dense behaviors, which can be adapted to different attacks. Then, the smooth boundary of dense rating (or co-visitation) behaviors is further segmented using higher order potentials, which is finally leveraged to determine the concerned injection behaviors. Extensive experiments on both synthetic data and real-world data demonstrate that the proposed IMIA-HCRF outperforms all baselines on various metrics. The detection performance of IMIA-HCRF can achieve an improvement of 7.8% for mixed profile injection attacks as well as 6% for mixed co-visitation injection attacks over the baselines in terms of FAR (false alarm rate) while keeping the highest DR (detection rate). Additional experiments on real-world data show that IMIA-HCRF brings an improvement with the advantage of 11.5% FAR in average compared with the baselines.

10 September 2018 in IEEE Access
Verified
Journal Article
Open access
ZYZhihai Yang
Zhihai Yang
QSQindong Sun
Qindong Sun
BZBeibei Zhang
Beibei Zhang
A rating system provides rating data about products or services, which is a key feature of e-commerce websites such as Amazon, TripAdvisor, and so on. In reality, rating systems generally suffer from threats of profile injection attacks or anomalous ratings due to the integration of collaborative recommendation techniques. To reduce these risks, a number of detection methods have been developed for defending such potential threats. However, they either directly calculate similarity between users or items to recognize attack profiles and genuine profiles, or utilize supervised learning methods by extracting features from user profiles for anomaly detection. In this paper, we propose a stepwise detection method to spot anomalous ratings or attacks, which bypasses the hard problems of similarity calculation and feature extraction. First, a part of samples are randomly selected from original user profiles for constructing a submatrix (rating matrix). A fast max-margin matrix factorization is then employed to make rating prediction. After that, suspected items can be captured by comprehensively analyzing both the distributions of mean prediction errors of items and users. Finally, anomalous ratings and potential attackers can be directly returned. Extensive experiments on MovieLens-100K data set demonstrate the effectiveness of the proposed approach compared with benchmarked methods. It is noteworthy that suspected items on a large-scale real-world data set, Amazon data, are detected by the proposed method and further analyzed from diverse perspectives, including rating distribution, rating intention, and time series analysis.

26 January 2022 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
ZYZhihai Yang
Zhihai Yang
QSQindong Sun
Qindong Sun
ZLZhaoli Liu
Zhaoli Liu
Recommender system, as a data-driven way to help customers locate products that match their interests, is increasingly critical for providing competitive customer suggestions in many web services. However, recommender systems are highly vulnerable to malicious injection attacks due to their fundamental vulnerabilities and openness. With the endless emergence of new attacks, how to provide a feasible way for defending different malicious threats against online recommendations is still an under-explored issue. In this paper, we explore a new way to defend malicious injection attacks through user intention understanding and influential neighbour disclosure. Specifically, we propose a detection approach, termed TBOS ( T hree B irds with O ne S tone), to deal with different malicious threats. In TBOS , we first develop the discrimination of attack target by combining global influence evaluation and risk attitude estimation of users. In order to make TBOS controllable, second, we propose to incorporate an optimal denoising mechanism to remove disturbed information before detection. To enhance the representativeness and predictability of detection model, finally, we propose to leverage a behavioral label propagation mechanism based on constructed label space for the determination of malicious injection behaviors. Extensive experiments on both synthetic and real data demonstrate that TBOS outperforms all baselines in different cases. Particularly, the detection performance of TBOS can achieve an improvement of 6.08% FAR (false alarm rate) for optimal-injection attacks, an improvement of 3.83% FAR in average for co-visitation injection attacks, as well as an improvement of 2.3% for profile injection attacks over benchmarks in terms of FAR while keeping the highest DR (detection rate). Additional experiments on real-world data show that TBOS brings an improvement with the advantage of 6.5% FAR in average compared with baselines.

10 September 2020 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
ZYZhihai Yang
Zhihai Yang
QSQindong Sun
Qindong Sun
YZYaling Zhang
Yaling Zhang
The increasing use of recommender systems as personalization recommendation services has stressed the demand for secure and usable abnormality detection techniques. With the emergence of new attacks, how to defend diverse malicious attacks for online recommendations is a challenging issue. Moreover, characterizing and evaluating sparse rating behaviors are a long-standing problem that still remains open, leading to an upsurge of research. This paper investigates probabilistic inference and trustworthiness evaluation of behavioral links according to a coupled association network converted from rating behaviors, and presents a unified detection framework from a novel perspective to spot diverse malicious threats. Firstly, an association graph is constructed from the original rating matrix based on both the inherent rating motivation of users and atomic propagation rules of coupled networks. Then, we evaluate the trustworthiness of link behaviors in the targeted network of associated cross network by exploiting a factor graph model of coupled network, and redetermine concerned links in the targeted network. Finally, suspicious users and items can be empirically inferred by comprehensively evaluating the trustworthiness of both links and nodes in the targeted network. Extensive experiments on synthetic and real-world data demonstrate the effectiveness of the proposed detection approach compared with competing benchmarks.

2 December 2025 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Open access
YFYan Feng
Yan Feng
ZYZhihai Yang
Zhihai Yang
KLKexin Li
Kexin Li
JLJianxin Li
Jianxin Li
PWPinghui Wang
Pinghui Wang
Zhiquan LiuZhiquan Liu
Zhiquan Liu
Recommender systems (RSs), as crucial components of online services, can help users efficiently obtain information they may like. In reality, RSs face long-term threats. Attackers manipulate recommendation results by injecting malicious data in order to obtain benefits. At present, research on the security of RSs lacks a comprehensive understanding of attack capabilities. Moreover, existing defense strategies have not yet been systematically associated with attack characteristics. More importantly, existing defense methods rarely focus on real unlabeled data in practical application scenarios for anomaly detection and forensics. Therefore, this survey systematically analyzes the security of RSs and provides new insights. Specifically, we first categorize attack models from an attack perspective into: attack strategies based on targets, attack strategies against security and privacy, attack strategies based on prior knowledge, and attack strategies against other RSs. From a perspective of defense, existing detection models, second, can be divided into: behavioral representation based on statistics, detection based on hidden features, detection against privacy attacks, anomaly discovery based on association mining, and abnormality forensics for real-world data. Finally, we propose several potential research directions aimed at providing guidance for the security research of RSs.