王垚飞
![]()
开通时间:..
最后更新时间:..
王垚飞|副教授、博士生导师
研究方向:生成式隐写与隐蔽通信、大模型安全、AIGC内容安全
诚招2027级推免研究生及本科科研实习生
现有推免硕士名额约3名。欢迎网络空间安全、计算机科学、人工智能、软件工程、数学等相关专业的同学联系。
我们聚焦人工智能时代的信息安全问题,近年来在CCS、NDSS、USENIX Security、IEEE S&P、IEEE TIFS、IEEE TDSC、ICML等顶级会议和期刊发表论文30余篇。课题组长期与中国科学技术大学俞能海教授和张卫明教授团队、安全技术企业及科研院所开展合作。
你可以参与的研究方向
生成式隐写与隐蔽通信:利用大语言模型和多模态生成模型,探索兼具安全性、容量和效率的新型隐蔽通信方法。
AIGC防伪、检测与内容溯源:研究面向文本、图像和音频生成模型的数字水印、内容检测与来源归因。
大模型安全与可信评测:研究大语言模型和多模态模型的对抗攻击、后门风险、安全评测及防御方法。
培养方式
课题组倡导“早进组、早选题”。入组后将根据学生基础和发展目标共同确定方向,并在文献阅读、科研选题、代码实现、实验设计和论文写作方面提供全过程指导。研一、研二以科研训练和成果积累为主;研三可根据个人规划选择学术深造、企业实习或就业。
课题组能够提供服务器资源、与中科大及合作单位交流的机会,以及学术会议、实习访学、硕博连读等支持。
我们更看重学生是否可靠、自驱、愿意持续投入。具有较好的编程、AI应用、数学或机器学习基础者优先。
欢迎发送简历联系:wyf@hfut.edu.cn
最新动态
2026年7月18日:祝贺 2025级郭金阳同学 的大语言模型水印论文 “PURA: Provably Unbiased and Robust Multi-Bit Watermarking for AI-Generated Text Attribution” 被信息安全领域四大顶会之一的 CCS 2026 接收!
2026年7月10日:祝贺 2025级王锐同学 的生成式文本隐写消除歧义论文 “ReTokSync: Self-Synchronizing Tokenization Disambiguation for Generative Linguistic Steganography” 被多媒体领域 CCF-A 类顶会 ACMMM 2026 接收!
2026年7月10日:祝贺 2024级王心茹同学 的大语言模型水印论文 “CheckMark: Robust Unbiased Multi-Bit Watermarking via CRC-Enhanced Candidate Decoding” 被多媒体领域 CCF-A 类顶会 ACMMM 2026 接收!
2026年6月4日:祝贺 2024级曹文钊同学 获得“阿里巴巴 千问C端事业群”的实习机会!
2026年5月1日:祝贺 2024级郑裕丰同学 的生成式图像隐写论文 “ASIR: Steganography for Diffusion Models via Antipodal Sampling and Iterative Recovery” 被人工智能顶会 ICML 2026 接收!
2026年4月7日:祝贺 2024级曹文钊同学 的隐写分析论文“Breaking the "Provable Security": Detecting Finite-Precision Artifacts in LLM-based Steganography via Low-Probability Vanishing”被ACL 2026 Findings接收!
2026年4月5日:祝贺 2023级方明同学 的音频伪造检测论文“LHCC: Cross-Domain Audio DeepfakeDetection via Consistency-Aware Fusion ofAcoustic and Semantic Representations”被中科院1区Information Fusion接收!
2026年3月18日:祝贺 2023级庞威龙同学 获得2026届合肥工业大学优秀毕业生和安徽省优秀毕业生荣誉!
2025年12月4日:祝贺 2023级庞威龙同学 的可证安全隐写论文“Breaking the Generative Steganography Trilemma: ANStega for Optimal Capacity, Efficiency, and Security”被信息安全领域四大顶会之一的 NDSS 2026 接收!
项目
1、国家自然科学基金青年基金,彩色图像隐写非对称失真设计与鲁棒性增强方法研究,主持,2024年1月-2026年12月,在研
2、基础加强重点项目子课题,XX理论构造研究,主持,2023年6月-2026年5月,在研
3、科技创新特区项目,面向大语言模型xxx标准及工具研究,主持,2023年12月-2025年11月,已结题
课题组学生成员
2026级:郑裕丰【博士】、蔡宇航【博士】、邓思雨、张阿康
2025级:郭金阳、唐晓戈、王锐、王鑫辰
2024级:王心茹、郑裕丰、柯晨读,联合指导:曹文钊
2023级:庞威龙(安徽省优秀毕业生)、石子悦、联合指导:荣先进【博士】、蔡宇航
2022级:联合指导:潘超【博士】
2021级:联合指导:彭银银【博士】、裴刚、汤允金
2020级:联合指导:张雨
本科生竞赛及大创工作
2024年,省级大创:《“追Gen溯源”——基于水印技术的大语言模型生成文本溯源系统》(2022级本科生:余奕俊、黄煜文、韩佳良、王磊、兰奕程)
2023年,省级大创:《基于水印嵌入的大型语言模型检测系统》(结题优秀)(2021级本科生:汪超、张飞龙、杜述超、廖国仲、彭德帅)
2023年,第五届全国高校计算机能力挑战赛:人工智能挑战赛全国决赛(国家级一等奖),嵌入式系统挑战赛全国决赛(国家级一等奖),“优秀指导老师”,嵌入式系统挑战赛区域赛(省级二等奖),程序设计挑战赛区域赛(省级二等奖),人工智能挑战赛区域赛(省级三等奖)(2021级本科生:汪超、王超凡、赵彦博)
2023年,全国大学生信息安全竞赛省赛:信息安全作品竞赛(省级一等奖),网络攻防赛(省级二等奖)(2021级本科生:汪超、张飞龙、杜述超、牛政翰、王杜涛)
恭喜2025届本科生汪超同学获得中国科学技术大学网络空间安全学院研究生offer!
代表性论文
Yaofei Wang, Weilong Pang, Kejiang Chen, Jinyang Ding, Donghui Hu*, Weiming Zhang*, Nenghai Yu. "Breaking the Generative Steganography Trilemma: ANStega for Optimal Capacity, Efficiency, and Security," Network and Distributed System Security (NDSS) Symposium 2026 (CCF A,信息安全领域四大顶级学术会议之一)
Li Yiming, Chen Kejiang, Wang Yaofei, Wang Guanjie, Zhang Weiming, Yu Nenghai, "CoAS: Composite Audio Steganography Based on Text and Speech Synthesis," IEEE Transactions on Information Forensics and Security, 2025.( CCF A,中科院SCI一区,信息安全领域顶级期刊)
Zexin Fan, Kejiang Chen, Yaofei Wang, Weiming Zhang, Nenghai Yu, "GIANT: Generated Image Adversarial Steganography Based on Narrowed Targeting", IEEE Transactions on Circuits and Systems for Video Technology, 2025. (中科院SCI一区)
Wang Y, Pei G, Chen K, et al. SparSamp: Efficient Provably Secure Steganography Based on Sparse Sampling[C]//34th USENIX Security Symposium, USENIX Security 2025, Seattle, WA, USA, 2025.(CCF A,信息安全领域四大顶级学术会议之一,相关报道:https://mp.weixin.qq.com/s/AlcisLxvln9V0A8bdlBVeQ)
Chao Pan, Donghui Hu*, Yaofei Wang*, Kejiang Chen, Yinyin Peng, Xianjin Rong, Chen Gu, Meng Li, "Rethinking Prefix-based Steganography for Enhanced Security and Efficiency," IEEE Transactions on Information Forensics and Security, 2025.( CCF A,中科院SCI一区,信息安全领域顶级期刊)
Chao Wang, Kejiang Chen, Zijin Yang, Yaofei Wang, Weiming Zhang, "AEDR: Training-Free AI-Generated Image Attribution via Autoencoder Double-Reconstruction", AAAI 2026 Oral (CCF A)
Y. Peng, Y. Wang*, D. Hu*, K. Chen, X. Rong, and W. Zhang, “LDStega: Practical and Robust Generative Image Steganography based on Latent Diffusion Models,” presented at the ACM Multimedia 2024, Jul. 2024. Accessed: Sep. 08, 2024. [Online]. Available: https://openreview.net/forum?id=kEqGgMgIlu(CCF A,相关报道:https://mp.weixin.qq.com/s/9YWILSAhKt4IBgbVtyj50w )
Q. Huang, C. Gu*, Y. Wang*, and D. Hu, “SpotAttack: Covering Spots on Surface to Attack LiDAR Based Autonomous Driving Systems,” IEEE Internet of Things Journal, pp. 1–1, 2024, doi: 10.1109/JIOT.2024.3452694.(中科院SCI一区,相关报道:https://mp.weixin.qq.com/s/Q7RAykFgjTLJvgHbq3_A8A)
Y. Peng, D. Hu*, Y. Wang*, K. Chen, G. Pei, and W. Zhang, “StegaDDPM: Generative Image Steganography based on Denoising Diffusion Probabilistic Model,” in Proceedings of the 31st ACM International Conference on Multimedia, in MM ’23. New York, NY, USA: Association for Computing Machinery, Oct. 2023, pp. 7143–7151. doi: 10.1145/3581783.3612514.(CCF A,相关报道:https://mp.weixin.qq.com/s/cb3mYwApwng1qjl5CksxXA)
Y. Wang, W. Zhang, W. Li, and N. Yu, “Non-Additive Cost Functions for JPEG Steganography Based on Block Boundary Maintenance,” IEEE Transactions on Information Forensics and Security, vol. 16, pp. 1117–1130, 2021, doi: 10.1109/TIFS.2020.3029908.( CCF A,中科院SCI一区,信息安全领域顶级期刊)
Y. Wang, W. Zhang, W. Li, X. Yu, and N. Yu, “Non-Additive Cost Functions for Color Image Steganography Based on Inter-Channel Correlations and Differences,” IEEE Transactions on Information Forensics and Security, vol. 15, pp. 2081–2095, 2020, doi: 10.1109/TIFS.2019.2956590.( CCF A,中科院SCI一区,信息安全领域顶级期刊)
Y. Wang, W. Li, W. Zhang, X. Yu, K. Liu, and N. Yu, “BBC++: Enhanced Block Boundary Continuity on Defining Non-Additive Distortion for JPEG Steganography,” IEEE Transactions on Circuits and Systems for Video Technology, pp. 1–1, 2020, doi: 10.1109/TCSVT.2020.3010554.(中科院SCI一区)
Y. Peng, D. Hu*, G. Pei, and Y. Wang*, “Image Steganography with Deep Orthogonal Fusion of Multi-Scale Channel Attention,” in ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr. 2024, pp. 4850–4854. doi: 10.1109/ICASSP48485.2024.10446373.(CCF B)
X. Cheng, Y. Wang*, C. Liu, D. Hu*, and Z. Su, “HiFi-GANw: Watermarked Speech Synthesis Via Fine-Tuning of HiFi-GAN,” IEEE Signal Processing Letters, pp. 1–5, 2024, doi: 10.1109/LSP.2024.3456673.(中科院SCI二区)
王垚飞,张卫明,陈可江*,周文柏,俞能海, “图像非加性隐写综述,” 网络与信息安全学报, vol. 7, no. 6, pp. 1–10, Dec. 2021, doi: 10.11959/j.issn.2096-109x.2021102.
J. Ding, K. Chen, Y. Wang, N. Zhao, W. Zhang, and N. Yu, “Discop: Provably Secure Steganography in Practice Based on ‘Distribution Copies,’” presented at the 2023 IEEE Symposium on Security and Privacy (SP), IEEE Computer Society, May 2023, pp. 2238–2255. doi: 10.1109/SP46215.2023.00155.(CCF A,信息安全领域四大顶级学术会议之一)
X. Wang, Y. Wang*, K. Chen, J. Ding, W. Zhang*, and N. Yu, “ICStega: Image Captioning-based Semantically Controllable Linguistic Steganography,” in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun. 2023, pp. 1–5. doi: 10.1109/ICASSP49357.2023.10095722.(CCF B)
J. Feng, Y. Wang, K. Chen, W. Zhang, and N. Yu, “An Effective Steganalysis for Robust Steganography with Repetitive JPEG Compression,” in ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, pp. 3084–3088. doi: 10.1109/ICASSP43922.2022.9747061.(CCF B)
K. Chen, H. Zhou, Y. Wang, M. Li, W. Zhang, and N. Yu, “Cover Reproducible Steganography via Deep Generative Models,” IEEE Transactions on Dependable and Secure Computing, pp. 1–13, 2022, doi: 10.1109/TDSC.2022.3217569.(中科院SCI一区)
K. Zeng, K. Chen, W. Zhang, and Y. Wang, “Upward Robust Steganography Based on Overflow Alleviation,” IEEE Transactions on Multimedia, vol. 26, pp. 299–312, 2024, doi: 10.1109/TMM.2023.3264628.( 中科院SCI一区)
K. Zeng, K. Chen, W. Zhang, Y. Wang, and N. Yu, “Robust Steganography for High Quality Images,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 33, no. 9, pp. 4893–4906, Sep. 2023, doi: 10.1109/TCSVT.2023.3250750.(中科院SCI一区)
Z. Su, M. Li, G. Zhang, Q. Wu, and Y. Wang, “Robust audio copy-move forgery detection on short forged slices using sliding window,” Journal of Information Security and Applications, vol. 75, p. 103507, Jun. 2023, doi: 10.1016/j.jisa.2023.103507.(中科院二区)
X. Yu, K. Chen, Y. Wang, W. Li, W. Zhang, and N. Yu, “Robust adaptive steganography based on generalized dither modulation and expanded embedding domain,” Signal Processing, vol. 168, p. 107343, Mar. 2020, doi: 10.1016/j.sigpro.2019.107343.(中科院二区)
K. Zeng, K. Chen, W. Zhang, Y. Wang, and N. Yu, “Improving Robust Adaptive Steganography via Minimizing Channel Errors,” Signal Processing, p. 108498, Feb. 2022, doi: 10.1016/j.sigpro.2022.108498.(中科院二区)
W. Li, K. Chen, W. Zhang, H. Zhou, Y. Wang, and N. Yu, “JPEG Steganography with Estimated Side-information,” IEEE Transactions on Circuits and Systems for Video Technology, pp. 1–1, 2019, doi: 10.1109/TCSVT.2019.2925118.(中科院SCI一区)
X. Yu, K. Chen, W. Zhang, Y. Wang, and N. Yu, “Improving the Embedding Strategy for Batch Adaptive Steganography,” in Digital Forensics and Watermarking, C. D. Yoo, Y.-Q. Shi, H. J. Kim, A. Piva, and G. Kim, Eds., in Lecture Notes in Computer Science. Cham: Springer International Publishing, 2019, pp. 248–260. doi: 10.1007/978-3-030-11389-6_19.
[1]
2017.9 -- 2022.6
中国科学技术大学
[2]
2013.9 -- 2017.6
西南交通大学