Shengyuan Bai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shengyuan Bai has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Nianmin Yao
School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, China
3 shared publications - Qibin Li
School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, China
3 shared publications Baoxun Wang
Platform and Content Group Tencent
1 shared publicationBowen Wu
Platform and Content Group Tencent
1 shared publication- Kaili Sun
Platform and Content Group Tencent
1 shared publication - Nai Zhou
Quan Cheng Laboratory
1 shared publication
Latest Publications
- Open Access
- 28 May 2026
- Published by MDPI AG in Future Internet
- Vol. 18 (6) , 292
A State-Assisted Authentication and Key Agreement Scheme for Lightweight Multi-RSU Access in VANETs
In highly dynamic vehicular ad hoc networks (VANETs), vehicles frequently move across the coverage areas of multiple roadside units (RSUs), making secure and efficient continuous vehicle-to-infrastructure access essential. However, repeated full authentication and key agreement for each new RSU access impose considerable computational and communication overhead. This paper proposes a state-assisted privacy-preserving mutual authentication and key agreement scheme for lightweight multi-RSU access in VANETs. The proposed scheme consists of initial and subsequent authentication phases. In the initial phase, elliptic curve cryptography (ECC) is used to achieve anonymous mutual authentication and session key establishment between vehicles and RSUs. In the subsequent authentication phase, a vehicle leverages follow-up authentication state securely forwarded by the previous RSU to complete fast authentication with a neighboring RSU using only hash and XOR operations. In addition, physically unclonable functions (PUFs) are deployed on both vehicles and RSUs to protect critical secrets. Security analysis shows that the proposed scheme achieves mutual authentication, anonymity preservation, and resistance to common attacks. Performance evaluation shows that it reduces the computational cost of subsequent authentication by more than 90% while maintaining low communication overhead.
- 28 May 2026
- Published by MDPI AG in Future Internet
- Vol. 18 (6) , 292
Open AccessA State-Assisted Authentication and Key Agreement Scheme for Lightweight Multi-RSU Access in VANETs
In highly dynamic vehicular ad hoc networks (VANETs), vehicles frequently move across the coverage areas of multiple roadside units (RSUs), making secure and efficient continuous vehicle-to-infrastructure access essential. However, repeated full authentication and key agreement for each new RSU access impose considerable computational and communication overhead. This paper proposes a state-assisted privacy-preserving mutual authentication and key agreement scheme for lightweight multi-RSU access in VANETs. The proposed scheme consists of initial and subsequent authentication phases. In the initial phase, elliptic curve cryptography (ECC) is used to achieve anonymous mutual authentication and session key establishment between vehicles and RSUs. In the subsequent authentication phase, a vehicle leverages follow-up authentication state securely forwarded by the previous RSU to complete fast authentication with a neighboring RSU using only hash and XOR operations. In addition, physically unclonable functions (PUFs) are deployed on both vehicles and RSUs to protect critical secrets. Security analysis shows that the proposed scheme achieves mutual authentication, anonymity preservation, and resistance to common attacks. Performance evaluation shows that it reduces the computational cost of subsequent authentication by more than 90% while maintaining low communication overhead.
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (22) , 23451-23459
Enhancing NLU in Large Language Models Using Adversarial Noisy Instruction Tuning
Instruction tuning has emerged as an effective approach that notably improves large language models (LLMs) performance, showing particular promise in natural language generation tasks by producing more diverse, coherent, and task-relevant outputs. However, extending instruction tuning to natural language understanding (NLU) tasks presents significant challenges, primarily due to the difficulty in achieving high-precision responses and the scarcity of large-scale, high-quality instruction data necessary for effective tuning. In this work, we introduce Adversarial Noisy Instruction Tuning (ANIT) to improve NLU performance on LLMs. First, we leverage low-resource techniques to construct noisy instruction datasets. Second, we employ semantic distortion-aware techniques to quantify the intensity of noise within these instructions. Last, we devise an adversarial training method that incorporates a noise response strategy to achieve noisy instruction tuning. ANIT enhances LLMs capability to detect and accommodate semantic distortions in noisy instructions, thereby augmenting their comprehension of task objectives and ability to generate more accurate responses. We evaluate our approach across diverse noisy instructions and semantic distortion quantification methods on multiple NLU tasks. Comprehensive empirical results demonstrate that our method consistently outperforms existing approaches across various experimental settings.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (22) , 23451-23459
Open AccessEnhancing NLU in Large Language Models Using Adversarial Noisy Instruction Tuning
Instruction tuning has emerged as an effective approach that notably improves large language models (LLMs) performance, showing particular promise in natural language generation tasks by producing more diverse, coherent, and task-relevant outputs. However, extending instruction tuning to natural language understanding (NLU) tasks presents significant challenges, primarily due to the difficulty in achieving high-precision responses and the scarcity of large-scale, high-quality instruction data necessary for effective tuning. In this work, we introduce Adversarial Noisy Instruction Tuning (ANIT) to improve NLU performance on LLMs. First, we leverage low-resource techniques to construct noisy instruction datasets. Second, we employ semantic distortion-aware techniques to quantify the intensity of noise within these instructions. Last, we devise an adversarial training method that incorporates a noise response strategy to achieve noisy instruction tuning. ANIT enhances LLMs capability to detect and accommodate semantic distortions in noisy instructions, thereby augmenting their comprehension of task objectives and ability to generate more accurate responses. We evaluate our approach across diverse noisy instructions and semantic distortion quantification methods on multiple NLU tasks. Comprehensive empirical results demonstrate that our method consistently outperforms existing approaches across various experimental settings.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 3478-3496
Anchoring-Guidance Fine-Tuning (AnGFT): Elevating Professional Response Quality in Role-Playing Conversational Agents
Qibin Li, Zhen Xu, Shengyuan Bai, Nianmin Yao, Kaili Sun, Bowen Wu, Ying Li, Baoxun Wang. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 3478-3496
Open AccessAnchoring-Guidance Fine-Tuning (AnGFT): Elevating Professional Response Quality in Role-Playing Conversational Agents
Qibin Li, Zhen Xu, Shengyuan Bai, Nianmin Yao, Kaili Sun, Bowen Wu, Ying Li, Baoxun Wang. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.