Rong Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Rong Wang has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Chin-Chen Chang
Department of Computer Science and Information Engineering, National Chin-Yi University of Technology, Taichung, Taiwan
3 shared publications Junchuan Liang
College of Computer Science, Sichuan Normal University, Chengdu, China
3 shared publications- Keping Yu
Hosei University
3 shared publications - Yan Zhu
Southwest Jiaotong University
3 shared publications Chaosheng Feng
2 shared publications- Junchuan Lianga
School of Computer Science Sichuan Normal University Chengdu China
2 shared publications
Latest Publications
- 18 September 2026
- Published by Elsevier in Journal of Information Security and Applications
- Vol. 103
ABE-FL: Efficient and secure federated learning based on CP-ABE with high-security elliptic curves
- 18 September 2026
- Published by Elsevier in Journal of Information Security and Applications
- Vol. 103
ABE-FL: Efficient and secure federated learning based on CP-ABE with high-security elliptic curves
- 3 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (3) , 5989-6004
UR-CP-ABE: CP-ABE With Flexible Construction Mechanism and Efficient User Revocation Capability for Access Control in the Cloud
Ciphertext-Policy Attribute-Based Encryption (CP-ABE) schemes with user revocation allow for dynamic updates to users' access rights. However, existing schemes often encounter issues such as low re-encryption efficiency, inflexible access control, and susceptibility to collusion attacks. To address these challenges, we propose UR-CP-ABE, an efficient user revocation scheme built upon a double encryption method. Specifically, UR-CP-ABE stores both valid and revoked users' identity information in a binary tree. This design enables flexible user authority revocation by modifying only the binary tree's relevant secret sub-items. Moreover, the scheme limits the scope of revocation-induced binary tree updates to a single sub-item. This key optimization resolves the critical issue where re-encryption overhead scales linearly with the number of attributes of revoked users. In addition, we eliminate the possibility of attackers constructing secret sub-keys, preventing the collusion attacks. UR-CP-ABE also supports bidirectional revocation, allowing for the revocation and restoration of user rights, which is not available in other related schemes. Our theoretical analysis and experiments demonstrate that UR-CP-ABE has better performance than other schemes, especially in the re-encryption stages. Moreover, UR-CP-ABE has been proved to be secure based on the decisional q-parallel BDHE hardness assumption in the standard model.
- 3 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (3) , 5989-6004
UR-CP-ABE: CP-ABE With Flexible Construction Mechanism and Efficient User Revocation Capability for Access Control in the Cloud
Ciphertext-Policy Attribute-Based Encryption (CP-ABE) schemes with user revocation allow for dynamic updates to users' access rights. However, existing schemes often encounter issues such as low re-encryption efficiency, inflexible access control, and susceptibility to collusion attacks. To address these challenges, we propose UR-CP-ABE, an efficient user revocation scheme built upon a double encryption method. Specifically, UR-CP-ABE stores both valid and revoked users' identity information in a binary tree. This design enables flexible user authority revocation by modifying only the binary tree's relevant secret sub-items. Moreover, the scheme limits the scope of revocation-induced binary tree updates to a single sub-item. This key optimization resolves the critical issue where re-encryption overhead scales linearly with the number of attributes of revoked users. In addition, we eliminate the possibility of attackers constructing secret sub-keys, preventing the collusion attacks. UR-CP-ABE also supports bidirectional revocation, allowing for the revocation and restoration of user rights, which is not available in other related schemes. Our theoretical analysis and experiments demonstrate that UR-CP-ABE has better performance than other schemes, especially in the re-encryption stages. Moreover, UR-CP-ABE has been proved to be secure based on the decisional q-parallel BDHE hardness assumption in the standard model.
- 18 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (2) , 4616-4627
Model Ownership Protection for Healthcare Consumer Electronics in Federated Edge Learning
With the rising demand for intelligent services and privacy protection in consumer artificial intelligence (AI), federated edge learning has emerged as a beacon for privacy-preserving distributed machine learning. This non-centralized approach offers distinct data privacy advantages, making it especially suitable for applications with strict privacy policies, such as consumer-centric healthcare systems. However, consumer electronics/devices in federated edge learning might unlawfully violate model ownership by duplicating or distributing models. Another concern is that a central server, if compromised, can become a conduit for model leakage, whether for profit motives or due to external intrusions, thus exacerbating the model ownership violation. To our knowledge, few works have focused on model ownership protection for federated edge learning in the consumer-centric healthcare domain. In this paper, we introduce a federated model ownership protection (FedMOP) approach. FedMOP is a model ownership safeguard and a formidable fortress built upon two core innovations. First, FedMOP can swiftly embed and replace watermarks during local training, allowing for the accurate identification and subsequent flagging of deceitful consumer devices. Second, FedMOP ensures that the server only accesses encrypted versions of the federated model, keeping the model a secret. Extensive evaluations demonstrate the robustness and effectiveness of FedMOP. We hope that FedMOP can light the way for surmounting similar ethical challenges in the broader realm of consumer-edge AI.
- 18 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (2) , 4616-4627
Model Ownership Protection for Healthcare Consumer Electronics in Federated Edge Learning
With the rising demand for intelligent services and privacy protection in consumer artificial intelligence (AI), federated edge learning has emerged as a beacon for privacy-preserving distributed machine learning. This non-centralized approach offers distinct data privacy advantages, making it especially suitable for applications with strict privacy policies, such as consumer-centric healthcare systems. However, consumer electronics/devices in federated edge learning might unlawfully violate model ownership by duplicating or distributing models. Another concern is that a central server, if compromised, can become a conduit for model leakage, whether for profit motives or due to external intrusions, thus exacerbating the model ownership violation. To our knowledge, few works have focused on model ownership protection for federated edge learning in the consumer-centric healthcare domain. In this paper, we introduce a federated model ownership protection (FedMOP) approach. FedMOP is a model ownership safeguard and a formidable fortress built upon two core innovations. First, FedMOP can swiftly embed and replace watermarks during local training, allowing for the accurate identification and subsequent flagging of deceitful consumer devices. Second, FedMOP ensures that the server only accesses encrypted versions of the federated model, keeping the model a secret. Extensive evaluations demonstrate the robustness and effectiveness of FedMOP. We hope that FedMOP can light the way for surmounting similar ethical challenges in the broader realm of consumer-edge AI.
- 28 August 2024
- Published by Springer Nature
- p. 214-227
PrivRBFN: Building Privacy-Preserving Radial Basis Function Networks Based on Federated Learning
- 28 August 2024
- Published by Springer Nature
- p. 214-227
PrivRBFN: Building Privacy-Preserving Radial Basis Function Networks Based on Federated Learning
- 11 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (1) , 1260-1273
Intelligent Web Spam Detection in the Consumer Internet of Things
The Consumer Internet of Things (CIoT) integrates the advantage of Internet of Things (IoT) technologies to provide convenience in consumers’ daily lives. With the rapid development of the CIoT, data collected from consumer smart devices has increased exponentially. In the CIoT, web pages, as internet information carriers, offer spammers opportunities to conduct security attacks, which could harm the CIoT systems. Inspired by this challenge, this paper introduces an intelligent feature extraction method, page2vec, and a new classification algorithm, RFiRF, to detect web spam in the CIoT. page2vec is based on a score propagation model, which calculates each page’s goodness and badness scores through the links of a web graph. It is observed that different scoring functions can produce different web page features. Based on this observation, 20 to 30 scoring functions are designed and incorporated into page2vec. This way, page2vec can automatically extract web page features from a web graph. Unfortunately, page2vec also brings a high dimensionality problem when constructing binary classifiers for spam detection. To address this problem, a new classification algorithm, called Random Forest in Random Forest (RFiRF), is proposed. RFiRF replaces a random forest’s meta-classifier (decision tree) with a random forest. It divides the sparse data space into dense sub-spaces by randomly sampling training instances and features. Experiments on two benchmark datasets show that 1) page2vec features are much more predictive than the raw link-based and node2vec features, and 2) RFiRF outperforms some classification algorithms in most cases when facing the high dimensionality problem. We hope this paper can give peers valuable insights into the CIoT security.
- 11 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (1) , 1260-1273
Intelligent Web Spam Detection in the Consumer Internet of Things
The Consumer Internet of Things (CIoT) integrates the advantage of Internet of Things (IoT) technologies to provide convenience in consumers’ daily lives. With the rapid development of the CIoT, data collected from consumer smart devices has increased exponentially. In the CIoT, web pages, as internet information carriers, offer spammers opportunities to conduct security attacks, which could harm the CIoT systems. Inspired by this challenge, this paper introduces an intelligent feature extraction method, page2vec, and a new classification algorithm, RFiRF, to detect web spam in the CIoT. page2vec is based on a score propagation model, which calculates each page’s goodness and badness scores through the links of a web graph. It is observed that different scoring functions can produce different web page features. Based on this observation, 20 to 30 scoring functions are designed and incorporated into page2vec. This way, page2vec can automatically extract web page features from a web graph. Unfortunately, page2vec also brings a high dimensionality problem when constructing binary classifiers for spam detection. To address this problem, a new classification algorithm, called Random Forest in Random Forest (RFiRF), is proposed. RFiRF replaces a random forest’s meta-classifier (decision tree) with a random forest. It divides the sparse data space into dense sub-spaces by randomly sampling training instances and features. Experiments on two benchmark datasets show that 1) page2vec features are much more predictive than the raw link-based and node2vec features, and 2) RFiRF outperforms some classification algorithms in most cases when facing the high dimensionality problem. We hope this paper can give peers valuable insights into the CIoT security.
- 10 April 2024
- Published by Elsevier in Journal of Information Security and Applications
- Vol. 83
A divide-and-conquer approach to privacy-preserving high-dimensional big data release
- 10 April 2024
- Published by Elsevier in Journal of Information Security and Applications
- Vol. 83
A divide-and-conquer approach to privacy-preserving high-dimensional big data release
- Open Access
A Survey on Federated Learning Poisoning Attacks and Defenses
As one kind of distributed machine learning technique, federated learning enables multiple clients to build a model across decentralized data collaboratively without explicitly aggregating the data. Due to its ability to break data silos, federated learning has received increasing attention in many fields, including finance, healthcare, and education. However, the invisibility of clients' training data and the local training process result in some security issues. Recently, many works have been proposed to research the security attacks and defenses in federated learning, but there has been no special survey on poisoning attacks on federated learning and the corresponding defenses. In this paper, we investigate the most advanced schemes of federated learning poisoning attacks and defenses and point out the future directions in these areas.
Open AccessA Survey on Federated Learning Poisoning Attacks and Defenses
As one kind of distributed machine learning technique, federated learning enables multiple clients to build a model across decentralized data collaboratively without explicitly aggregating the data. Due to its ability to break data silos, federated learning has received increasing attention in many fields, including finance, healthcare, and education. However, the invisibility of clients' training data and the local training process result in some security issues. Recently, many works have been proposed to research the security attacks and defenses in federated learning, but there has been no special survey on poisoning attacks on federated learning and the corresponding defenses. In this paper, we investigate the most advanced schemes of federated learning poisoning attacks and defenses and point out the future directions in these areas.
- Open Access
Covert Communication Based on the Poisoning Attack in Federated Learning
Covert communication has become an important area of research in computer security. It involves hiding specific information on a carrier for message transmission and is often used to transmit private data, military secrets, and even malware. In deep learning, many methods have been developed for hiding information in models to achieve covert communication. However, these methods are not applicable to federated learning, where model aggregation invalidates the exact information embedded in the model by the client. To address this problem, we propose a novel method for covert communication in federated learning based on the poisoning attack. Our approach achieves 100% accuracy in covert message transmission between two clients and is shown to be both stealthy and robust through extensive experiments. However, existing defense methods are limited in their effectiveness against our attack scheme, highlighting the urgent need for new protection methods to be developed. Our study emphasizes the necessity of research in covert communication and serves as a foundation for future research in federated learning attacks and defenses.
Open AccessCovert Communication Based on the Poisoning Attack in Federated Learning
Covert communication has become an important area of research in computer security. It involves hiding specific information on a carrier for message transmission and is often used to transmit private data, military secrets, and even malware. In deep learning, many methods have been developed for hiding information in models to achieve covert communication. However, these methods are not applicable to federated learning, where model aggregation invalidates the exact information embedded in the model by the client. To address this problem, we propose a novel method for covert communication in federated learning based on the poisoning attack. Our approach achieves 100% accuracy in covert message transmission between two clients and is shown to be both stealthy and robust through extensive experiments. However, existing defense methods are limited in their effectiveness against our attack scheme, highlighting the urgent need for new protection methods to be developed. Our study emphasizes the necessity of research in covert communication and serves as a foundation for future research in federated learning attacks and defenses.
- Open Access
- 5 August 2022
- Published by Springer Nature in Research Square
A Survey on Federated Learning PoisoningAttacks and Defenses
As one kind of distributed machine learning technique, federated learning enables multiple clients to build a model across decentralized datacollaboratively without explicitly aggregating the data. Due to its abilityto break data silos, federated learning has received increasing attentionin many fields, including finance, healthcare, and education. However,the invisibility of clients’ training data and the local training process result in some security issues. Recently, many works have beenproposed to research the security attacks and defenses in federatedlearning, but there has been no special survey on poisoning attacks onfederated learning and the corresponding defenses. In this paper, weinvestigate the most advanced schemes on federated learning poisoningattacks and defenses and point out the future directions in these areas.
- 5 August 2022
- Published by Springer Nature in Research Square
Open AccessA Survey on Federated Learning PoisoningAttacks and Defenses
As one kind of distributed machine learning technique, federated learning enables multiple clients to build a model across decentralized datacollaboratively without explicitly aggregating the data. Due to its abilityto break data silos, federated learning has received increasing attentionin many fields, including finance, healthcare, and education. However,the invisibility of clients’ training data and the local training process result in some security issues. Recently, many works have beenproposed to research the security attacks and defenses in federatedlearning, but there has been no special survey on poisoning attacks onfederated learning and the corresponding defenses. In this paper, weinvestigate the most advanced schemes on federated learning poisoningattacks and defenses and point out the future directions in these areas.
- Open Access
- 9 October 2021
- Published by SPIE-Intl Soc Optical Eng
- Vol. 11905, 32
Security analysis and improvement of source independent quantum random number generators with imperfect devices
Recently, a source-independent quantum random number generator (SI-QRNG), which can generate secure random numbers with untrusted sources, has been realized. However, the measurement loopholes of the trusted but imperfect devices used in SI-QRNGs have not yet been fully explored. Here, we point out and evaluate the security loopholes of practical imperfect measurement devices in SI-QRNGs. We also provide corresponding countermeasures to prevent these information leakages by recalculating the conditional minimum entropy and adding a monitor. Furthermore, by taking into account the finite-size effect, we show that the influence of the afterpulse can exceed that of the finite-size effect with the large number of sampled rounds. Our protocol is simple and effective, and it promotes the security of SI-QRNG in practice as well as the compatibility with high-speed measurement evices, thus paving the way for constructing ultrafast and security-certified commercial SI-QRNG systems.
- 9 October 2021
- Published by SPIE-Intl Soc Optical Eng
- Vol. 11905, 32
Open AccessSecurity analysis and improvement of source independent quantum random number generators with imperfect devices
Recently, a source-independent quantum random number generator (SI-QRNG), which can generate secure random numbers with untrusted sources, has been realized. However, the measurement loopholes of the trusted but imperfect devices used in SI-QRNGs have not yet been fully explored. Here, we point out and evaluate the security loopholes of practical imperfect measurement devices in SI-QRNGs. We also provide corresponding countermeasures to prevent these information leakages by recalculating the conditional minimum entropy and adding a monitor. Furthermore, by taking into account the finite-size effect, we show that the influence of the afterpulse can exceed that of the finite-size effect with the large number of sampled rounds. Our protocol is simple and effective, and it promotes the security of SI-QRNG in practice as well as the compatibility with high-speed measurement evices, thus paving the way for constructing ultrafast and security-certified commercial SI-QRNG systems.