学术成果 |
（一）政策及相关标准研究 （1）参与起草《全球人工智能治理倡议》，由习近平总书记在2023年10月18日第三届“一带一路”国际合作高峰论坛开幕式主旨演讲中正式发布。 （2）参与起草《生成式人工智能服务管理暂行办法》，是全球首个针对生成式人工智能的监管办法，已于2023年8月15日正式施行。 （3）参与起草了《生成式人工智能服务安全基本要求》，规范了生成式人工智能服务在安全方面的基本要求，包括语料安全、模型安全、安全措施、安全评估等。 （4）参与起草了《网络安全标准实践指南——生成式人工智能服务内容标识方法》，该实践指南围绕文本、图片、音频、视频四类生成内容给出了内容标识方法，可用于指导生成式人工智能服务提供者提高安全管理水平。 （5）参与起草了国家标准《信息安全技术——生成式人工智能预训练和优化训练数据安全规范》、国家标准《信息安全技术——生成式人工智能人工标注安全规范》，分别用于指导生成式人工智能训练数据和标注过程的规范。 （6）支撑中央网信办建设国内大语言模型安全检测平台，对全国备案上线提供服务的大模型开展安全巡检。 （二）期刊论文 (‘#’表示共同一作,‘*’表示通信作者) [1]. Zhongliang Yang, Guo Xiaoqin, Chen Zimin, Huang Yongfeng* and Zhang Yujin. RNN-stega: Linguistic steganography based on recurrent neural networks[J]. IEEE Transactions on Information Forensics and Security, 2019, 14(5): 1280-1295. (1区, CCF A, TOP) [2]. Zhongliang Yang, Zhang Siyu, Hu Yuting, Hu Zhiwen, Huang Yongfeng*. VAE-Stega: Linguistic steganography based on variational auto-encoder[J]. IEEE Transactions on Information Forensics and Security, 2020, 16: 88. (1区, CCF A, TOP, ESI 热点论文) [3]. Zhongliang Yang, Hao Yang, Ching-Chun Chang, Yongfeng Huang, Real-Time Steganalysis for Streaming Media Based on Multi-Channel Convolutional Sliding Windows, Knowledge Based System, 2022, 237: 107561. (1区, TOP) [4]. Jinshuai Yang, Zhongliang Yang*, Jiajun Zhou, Haoqin Tu, Yongfeng Huang. Linguistic Steganalysis Toward Social Network. IEEE Transactions on Information Forensics and Security, 2022, 18: 859-871. (1区, CCF A, TOP) [5]Wang H, Yang Z*, Yang J, et al. Linguistic steganalysis in few-shot scenario[J]. IEEE Transactions on Information Forensics and Security, 2023. (1区, CCF A, TOP) [6]Chenwei Huang; Zhongliang Yang*; Zhiwen Hu; Jinshuai Yang; Haochen Qi; Jian Zhang*; Lei Zheng*. DNA Synthetic Steganography Based on Conditional Probability Adaptive Coding[J]. IEEE Transactions on Information Forensics and Security, 2023.(1区, CCF A, TOP) [7]. Haoqin Tu, Zhongliang Yang*, Jinshuai Yang, Linna Zhou, Yongfeng Huang. FET-LM: Flow-Enhanced Variational Autoencoder for Topic-Guided Language Modeling. IEEE Transactions on Neural Networks and Learning Systems, 2022. (1区, TOP, IF = 14.255) [8]Ding C, Fu Z, Yang Z, et al. Context-aware Linguistic Steganography Model Based on Neural Machine Translation[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023. [9]. Zhongliang Yang, Lingyun Xiang*, Siyu Zhang, Xingming Sun and Yongfeng Huang, Linguistic Generative Steganography with Enhanced Cognitive-Imperceptibility, IEEE Signal Processing Letters, 2021. [10]. Zhongliang Yang, Huang Yongfeng* and Zhang Yujin, "A Fast and Efficient Text Steganalysis Method," in IEEE Signal Processing Letters, vol. 26, no. 4, April 2019. [11]. Zhongliang Yang, Wang Ke, Li Jian, Huang Yongfeng* and Zhang Yujin, "TS-RNN: Text Steganalysis Based on Recurrent Neural Networks", in IEEE Signal Processing Letters, vol. 26, no. 12, pp. 1743-1747, Dec. 2019. [12]. Haoqin Tu, Zhongliang Yang*, Jinshuai Yang, Siyu Zhang, Yongfeng Huang. PCAE: A framework of plug-in conditional auto-encoder for controllable text generation. Knowledge Based System, 2022, 256: 109766. (1区, TOP) [13]. Fang Chen, Ziwei Shi, Zhongliang Yang*, Yongfeng Huang. Recurrent synchronization network for emotion-cause pair extraction. Knowledge Based System, 2022. (1区, TOP) [14]. Fang Chen, Zhongliang Yang*, Yongfeng Huang. A multi-task learning framework for end-to-end aspect sentiment triplet extraction. Neurocomputing, 2022. [15]. Siyu Zhang, Zhongliang Yang*, Jinshuai Yang, Yongfeng Huang, Linguistic Steganography: From Symbolic Space to Semantic Space, IEEE Signal Processing Letters, 2021, 28, 11-15. (Featured Articles) [16]. Jinshuai Yang, Zhongliang Yang*, Siyu Zhang, Haoqin Tu. SeSy: Linguistic Steganalysis Framework Integrating Semantic and Syntactic Features, IEEE Signal Processing Letters, 2021, 28. [17]. Hao Yang, Zhongliang Yang*, Yongjian Bao, Sheng Liu, Yongfeng Huang*, Fast Steganalysis Method for VoIP Streams, IEEE Signal Processing Letters, 2019, 27, 286-290. [18]. Fulian Yin, Meiqi Ji, Zhongliang Yang, Zhaoliang Wu, Xinyu Xia, Tongtong Xing, Yuwei She, Zhiwen Hu. Exploring the determinants of global vaccination campaigns to combat COVID-19. Humanities and Social Sciences Communications , 2022, 9(1): 1-13. (Nature 子刊) [19] Haochen Qi†, Zhiwen Hu†, Zhongliang Yang, Jian Zhang*, Jie Jayne Wu*, Cheng Cheng, Chunchang Wang, Lei Zheng*. A capacitive aptasensor coupled with microfluidic enrichment for real-time detection of trace SARS-CoV-2 nucleocapsid protein. Analytical Chemistry. 1-21 (2022). (ESI 高被引) （三）会议论文 [1]. Pang K, Yang J, Gao Y, et al. CATS: Connection-Aware and Interaction-Based Text Steganalysis in Social Networks[C]//International Conference on Neural Information Processing. Singapore: Springer Nature Singapore, 2023: 109-121. [2] Wang H, Yang Z, Yang J, et al. Hi-Stega: A Hierarchical Linguistic Steganography Framework Combining Retrieval and Generation[C] //International Conference on Neural Information Processing. Singapore: Springer Nature Singapore, 2023: 41-54. [3] Yang J, Yang Z, Ge X, et al. LINK: Linguistic Steganalysis Framework with External Knowledge[C]//ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023: 1-5. [4] Qi T, Wu F, Wu C, et al. Fairvfl: A fair vertical federated learning framework with contrastive adversarial learning[J]. Advances in neural information processing systems, 2022, 35: 7852-7865. [5] Zou J, Wu S, Yang Z, et al. Aspect-level sentiment classification based on graph attention network with BERT[C]//International Conference on Artificial Intelligence and Security. Cham: Springer International Publishing, 2022: 231-244. [6] Zou J, Wu S, Yang Z, et al. Association Extraction and Recognition of Multiple Emotion Expressed in Social Texts[C]//International Conference on Adaptive and Intelligent Systems. Cham: Springer International Publishing, 2022: 420-430. [7]. Siyu Zhang, Zhongliang Yang*, et al. Provably Secure Generative Linguistic Steganography. Accepted by the 2021 Conference on Empirical Methods in Natural Language Processing: Findings. [8]. Huili Wang, Zhongliang Yang*, Yuting Hu, Zhen Yang, Yongfeng Huang. Fast Detection of Heterogeneous Parallel Steganography for Streaming Voice. ACM IH&MMSec,2021. [9] Zhongliang Yang, Peng Xueshun, Huang Yongfeng. A sudoku matrix-based method of pitch period steganography in low-rate speech coding[C]//International Conference on Security and Privacy in Communication Systems. Springer, Cham, 2017: 752-762. [10]. Zhongliang Yang, Wei Nan, Liu Qinhe, Huang Yongfeng, Zhang Yujin. GAN-TStega: Text Steganography Based on Generative Adversarial Networks [C]//International Workshop on Digital Watermarking. Springer, Cham, 2019. [11]. Zhongliang Yang, Hu Yuting, Huang Yongfeng, Zhang Yujin. Behavioral Security in Covert Communication Systems [C]//International Workshop on Digital Watermarking. Springer, 2019. [12]. Zhongliang Yang, Wang ke, Ma Sai, Huang Yongfeng, Kang Xiangui, Zhao Xianfeng. IStego100K: Large-scale Image Steganalysis Dataset [C]//International Workshop on Digital Watermarking. Springer, Cham, 2019. （四）专利 [1].周琳娜，杨忠良; 王壮; 陈学楷; 郭胜男; 基于聚类和集成学习的不平衡语言隐写分析方法及装置 [2] 张鉴; 杨忠良; 黄陈炜; 戚昊琛; 尤方朔; 陈炯铭，一种序列生成式DNA隐写方法和评价方法。 [3] 黄永峰; 杨浩; 杨忠良; 鲍永健; 杨震，基于双向循环神经网络的网络语音流隐写分析方法及装置。 [4] 黄永峰，杨忠良，杨震，胡雨婷，袁志刚，武楚涵，基于马尔可夫模型和哈夫曼编码的文本隐写方法及装置。 [5] 黄永峰; 杨浩; 鲍永健; 杨忠良; 杨震，基于系数相关模型的MP3音频隐写分析方法及装置 [6] 黄永峰，杨忠良，王颗，杨震，胡雨婷，武楚涵，基于循环神经网络的文本隐写检测方法及系统。 [7] 黄永峰; 杨忠良; 胡雨婷; 杨震; 陈放; 吴思行; 黄琬婷，基于容量自适应收缩机制载体生成式文本隐写方法及装置。 [8] 黄永峰，杨浩，杨忠良，鲍永健，基于层次注意力网络模型的语音流隐写分析方法及系统。 [9] 黄永峰; 吴方照; 刘佳伟; 袁志刚; 吴思行; 杨忠良，微博情感分类器的构建方法及构建装置。
|
