Shulan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shulan Wang has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
Haiyan Wang
Cyberspace Security Research Center, Peng Cheng Laboratory, Shenzhen, China
2 shared publications- Jianqiang Li
Shenzhen University
2 shared publications - Junwei Zhou
Wuhan University of Technology
2 shared publications - Kaitai Liang
Department of Computing, University of Turku, Turku, Finland
2 shared publications - Chenbin Zhao
School of Mathematics and Big Data, Anhui University of Science and Technology, Huainan, China
1 shared publication - Chengshun Jiang
School of Artificial Intelligence Nanchang Institute of Science and Technology Nanchang China
1 shared publication
Latest Publications
- 17 July 2026
- Published by Springer Nature
- p. 522-540
Deepfake Forensics Adapter: A Dual-Stream Network for Generalizable Deepfake Detection
- 17 July 2026
- Published by Springer Nature
- p. 522-540
Deepfake Forensics Adapter: A Dual-Stream Network for Generalizable Deepfake Detection
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21, 7032-7047
SHRD: A Scalable Scheme for Hierarchical File Sharing With Rank-Aware Dissemination
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21, 7032-7047
SHRD: A Scalable Scheme for Hierarchical File Sharing With Rank-Aware Dissemination
- 16 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 32 (10709908) , 1695-1699
Multiple Model Estimation via Variable Structure With Spatiotemporal Primal-Dual Projection
This letter presents a robust multiple-model (MM) estimator based on variable structure multiple Gaussian importance filtering (VSMGIF) with spatiotemporal primal-dual projection. In VSMGIF, orthogonal-velocity-constrained maneuver models are introduced, and spatiotemporal causal constraints are incorporated within clearly defined projection zones. This framework enables approximate Rao-Blackwellization, while combining Gaussian mixture models with importance sampling to handle nonlinear, non-Gaussian hybrid estimation. Model probabilities and sample weights are adaptively corrected using all available information. Experimental results demonstrate that VSMGIF effectively mitigates coordinate coupling and Gaussian truncation errors in bearing-only tracking.
- 16 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 32 (10709908) , 1695-1699
Multiple Model Estimation via Variable Structure With Spatiotemporal Primal-Dual Projection
This letter presents a robust multiple-model (MM) estimator based on variable structure multiple Gaussian importance filtering (VSMGIF) with spatiotemporal primal-dual projection. In VSMGIF, orthogonal-velocity-constrained maneuver models are introduced, and spatiotemporal causal constraints are incorporated within clearly defined projection zones. This framework enables approximate Rao-Blackwellization, while combining Gaussian mixture models with importance sampling to handle nonlinear, non-Gaussian hybrid estimation. Model probabilities and sample weights are adaptively corrected using all available information. Experimental results demonstrate that VSMGIF effectively mitigates coordinate coupling and Gaussian truncation errors in bearing-only tracking.
- 5 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (4) , 4456-4471
LogDLR: Unsupervised Cross-System Log Anomaly Detection Through Domain-Invariant Latent Representation
Log anomaly detection aims to discover abnormal events from massive log data to ensure the security and reliability of software systems. However, due to the heterogeneity of log formats and syntaxes across different systems, existing log anomaly detection methods often need to be designed and trained for specific systems, lacking generalization ability. To address this challenge, we propose LogDLR, a novel unsupervised cross-system log anomaly detection method. The core idea of LogDLR is to use universal sentence embeddings and a Transformer-based autoencoder to extract domain-invariant latent representations from log entries, which can effectively adapt to log format changes and capture semantic information and dependencies in log sequences. To obtain domain-invariant latent representations, we adopt a domain-adversarial training strategy, introducing a domain discriminator that competes with the Transformer-based encoder through a gradient reversal layer, forcing the encoder to learn shared knowledge between different system logs. Finally, the Transformer-based decoder detects anomalies based on the domain-invariant representations obtained by the encoder. We evaluate LogDLR in simulated cross-system scenarios using three publicly available log datasets. The experimental results show that LogDLR can handle heterogeneous logs effectively in cross-system scenarios and achieve efficient and accurate anomaly detection on both source and target systems.
- 5 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (4) , 4456-4471
LogDLR: Unsupervised Cross-System Log Anomaly Detection Through Domain-Invariant Latent Representation
Log anomaly detection aims to discover abnormal events from massive log data to ensure the security and reliability of software systems. However, due to the heterogeneity of log formats and syntaxes across different systems, existing log anomaly detection methods often need to be designed and trained for specific systems, lacking generalization ability. To address this challenge, we propose LogDLR, a novel unsupervised cross-system log anomaly detection method. The core idea of LogDLR is to use universal sentence embeddings and a Transformer-based autoencoder to extract domain-invariant latent representations from log entries, which can effectively adapt to log format changes and capture semantic information and dependencies in log sequences. To obtain domain-invariant latent representations, we adopt a domain-adversarial training strategy, introducing a domain discriminator that competes with the Transformer-based encoder through a gradient reversal layer, forcing the encoder to learn shared knowledge between different system logs. Finally, the Transformer-based decoder detects anomalies based on the domain-invariant representations obtained by the encoder. We evaluate LogDLR in simulated cross-system scenarios using three publicly available log datasets. The experimental results show that LogDLR can handle heterogeneous logs effectively in cross-system scenarios and achieve efficient and accurate anomaly detection on both source and target systems.
- 28 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. 56 (00939994) , 1
A Fast CP-ABE System for Cyber-Physical Security and Privacy in Mobile Healthcare Network
A healthcare network as a new context-aware cyber-physical system (CPS) includes embedded sensors, Internet of Things technology, and cloud computing. With the intellectualization of mobile terminal devices, mobile healthcare networks are automatically generated and can provide convenient healthcare services and real-time communication. However, two problems in the CPS need to resolved. A solution to the first problem is to mitigate the computational and storage cost of a mobile terminal. A solution to the second problem is to provide the cyber-physical privacy and security for healthcare data. Ciphertext-policy attribute-based encryption (CP-ABE) can provide data privacy and secure sharing in an open environment. In this article, a fast CP-ABE scheme is provided in order to satisfy the use of mobile terminal devices with low computational and storage power. In the proposed scheme, the work of a system can deliver expensive computational tasks to semitrusted third parties, ensuring a constant number of simple local computations. The scheme can also verify the correctness of the decryption result by using a Boneh–Lynn–Shacham short signature scheme. The CP-ABE scheme not only ensures the cyber-physical security of healthcare data, but also reduces the local load from the efficiency analysis and experimental results.
- 28 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. 56 (00939994) , 1
A Fast CP-ABE System for Cyber-Physical Security and Privacy in Mobile Healthcare Network
A healthcare network as a new context-aware cyber-physical system (CPS) includes embedded sensors, Internet of Things technology, and cloud computing. With the intellectualization of mobile terminal devices, mobile healthcare networks are automatically generated and can provide convenient healthcare services and real-time communication. However, two problems in the CPS need to resolved. A solution to the first problem is to mitigate the computational and storage cost of a mobile terminal. A solution to the second problem is to provide the cyber-physical privacy and security for healthcare data. Ciphertext-policy attribute-based encryption (CP-ABE) can provide data privacy and secure sharing in an open environment. In this article, a fast CP-ABE scheme is provided in order to satisfy the use of mobile terminal devices with low computational and storage power. In the proposed scheme, the work of a system can deliver expensive computational tasks to semitrusted third parties, ensuring a constant number of simple local computations. The scheme can also verify the correctness of the decryption result by using a Boneh–Lynn–Shacham short signature scheme. The CP-ABE scheme not only ensures the cyber-physical security of healthcare data, but also reduces the local load from the efficiency analysis and experimental results.
- 31 July 2019
- Published by Springer Nature in International Journal of Information Security
- Vol. 19 (3) , 303-310
An improved FOO voting scheme using blockchain
- 31 July 2019
- Published by Springer Nature in International Journal of Information Security
- Vol. 19 (3) , 303-310
An improved FOO voting scheme using blockchain
- 25 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 15 (12) , 6500-6509
An Efficient Attribute-Based Encryption Scheme With Policy Update and File Update in Cloud Computing
Recently, more and more users and enterprises have entrusted data storage and platform construction to proxy cloud service provider (PCSP) through cloud technology. Under this background, the attribute-based encryption (ABE) mechanism is an alternative to fill the drawbacks of the traditional encryption through flexible fine-grained access policy and collusion prevention. However, there exist some security issues when the access policy and file need to be updated in practical applications. And the ABE has the problems of excessive computation and storage costs. In this article, an efficient ciphertext-policy ABE scheme with policy update and file update is proposed in cloud computing. The ciphertext components generated by first encryption can be shared when the policy update and file update happens. It reduces the storage and communication costs of the client, and the computational cost of the PCSP. Moreover, the proposed scheme is proved to be secure under the assumption of decision q-parallel bilinear Diffie–Hellman exponent (BDHE). Finally, experimental simulation shows that the proposed scheme is highly efficient in terms of policy update and file update.
- 25 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 15 (12) , 6500-6509
An Efficient Attribute-Based Encryption Scheme With Policy Update and File Update in Cloud Computing
Recently, more and more users and enterprises have entrusted data storage and platform construction to proxy cloud service provider (PCSP) through cloud technology. Under this background, the attribute-based encryption (ABE) mechanism is an alternative to fill the drawbacks of the traditional encryption through flexible fine-grained access policy and collusion prevention. However, there exist some security issues when the access policy and file need to be updated in practical applications. And the ABE has the problems of excessive computation and storage costs. In this article, an efficient ciphertext-policy ABE scheme with policy update and file update is proposed in cloud computing. The ciphertext components generated by first encryption can be shared when the policy update and file update happens. It reduces the storage and communication costs of the client, and the computational cost of the PCSP. Moreover, the proposed scheme is proved to be secure under the assumption of decision q-parallel bilinear Diffie–Hellman exponent (BDHE). Finally, experimental simulation shows that the proposed scheme is highly efficient in terms of policy update and file update.