李晓龙

博士 、教授

基本信息

办公电话： 电子邮件： lixl@bjtu.edu.cn
通讯地址：北京市海淀区上园村3号，第九教学楼北606 邮编：100044

教育背景

2002/9–2006/3，法国卡尚高等师范学校（ENS de Cachan，France），专业：数学，博士学位，导师：Yves Meyer

2001/9–2002/7，法国巴黎综合理工学校（Ecole Polytechnique，France），专业：数学、视觉和模式识别，硕士学位，导师：Yves Meyer

1999/7–2001/7，法国巴黎综合理工学校（Ecole Polytechnique，France），专业：数学，工程师学位

1995/9–1999/7，北京大学，专业：基础数学，学士学位

工作经历

2016/11-至今，北京交通大学，计算机与信息技术学院

2006/06-2016/10，北京大学，计算机科学技术研究所

个人简介：主要研究方向是机器学习和多媒体内容安全，包括优化方法、对抗样本、数字水印、数字取证等。发表学术论文百余篇，其中包含8篇ESI高被引。主持国家自然科学基金重点项目一项、面上项目三项、重点研发计划子课题两项。获省部级一等奖一次、二等奖三次、三等奖一次。据Google Citation统计，学术成果已被国内外同行引用超万次。2020-2025连续六年入选爱思唯尔中国高被引学者榜单。

招生信息：感兴趣同学请邮件联系（附个人简历和本科成绩单）：lixl@bjtu.edu.cn。


研究方向

  • 数字媒体信息处理与智能分析
  • 新一代电子信息技术
  • 软件工程
  • 人工智能
  • 大数据技术与工程
  • 机器学习与认知计算
  • 计算机技术

招生专业

  • 新一代电子信息技术（含量子技术等）硕士
  • 软件工程硕士
  • 人工智能硕士
  • 大数据技术与工程硕士
  • 新一代电子信息技术（含量子技术等）博士
  • 人工智能博士
  • 计算机科学与技术硕士
  • 计算机技术硕士
  • 计算机技术博士
  • 计算机科学与技术博士
  • 软件工程博士

科研项目

国家自然科学基金面上项目，62372037，广义失真下的图像可逆隐藏，2024/01-2027/12，主持

国家自然科学基金国际(地区)合作与交流项目，62261160653，基于信息隐藏的数字媒体内容安全理论与关键技术研究，2023/01-2025/12，合作单位主持人

山东省自然科学基金智慧计算联合基金重点项目，ZR2022LZH011，图像视频隐私保护关键技术与技术标准研究，2023/01-2025/12，合作单位主持人

国家自然科学基金面上项目，61972031，基于多直方图的JPEG图像可逆信息隐藏，2020/01-2023/12，主持

国家自然科学基金通用技术基础研究联合基金重点项目，U1736213，适应多种信道的安全隐写：基础理论和关键技术研究，2018/01-2021/12，主持

国家自然科学基金面上项目，61572052，高保真可逆图像信息隐藏关键问题研究，2016/01-2019/12，主持

教学工作

研究生课程：智能计算数学基础（C402017B，48学时）

研究生课程：凸优化理论与应用（M602022B，32学时）

本科课程：人工智能数学基础（M302032B，48学时）

论文/期刊

[1] Xiang Li, Xiaolong Li, and Yao Zhao, “MME-based piecewise data transformation and 2D mapping optimization for reversible data hiding,” IEEE TMM, 2026, to appear.
[2] Mengyao Xiao, Xiaolong Li, Jian Li, Qingchao Jiang, and Yao Zhao, “High-capacity reversible data hiding for JPEG images using ternary matrix embedding,” IEEE TMM, 2026, to appear.
[3] Shuo Chen, Xiaolong Li, Jiaying Peng, and Yao Zhao, “On the convergence direction of gradient descent,” in Proc. ICLR, 2026, to appear.
[4] Xiang Li, Xiaolong Li, Shaohai Hu, and Yao Zhao, “Steganography-enhanced prediction-error expansion: A novel reversible data hiding framework,” IEEE TCSVT, 35(3), pp. 2701-2711, 2025.
[5] Wenjie Li, Xiaolong Li, Rongrong Ni, and Yao Zhao, “Extracting high-discriminative features for detecting double JPEG compression with the same quantization matrix,” IEEE TCSVT, 35(5), pp. 4727-4739, 2025.
[6] Jingtian Wang, Xiaolong Li, Bin Ma, and Yao Zhao, “Boosting transferability of adversarial examples with spatio-temporal context,” ACM TOMM, 21(10), pp. 297:1-297:22, 2025.
[7] Xiaolong Liu, Yang Yu, Xiaolong Li, and Yao Zhao, “MCL: Multimodal contrastive learning for deepfake detection,” IEEE TCSVT, 34(4), pp. 2803-2813, 2024.
[8] Kuiyuan Sun, Xiaolong Liu, Xiaolong Li, Yao Zhao, and Wei Wang, “Multi-modal driven pose-controllable talking head generation,” ACM TOMM, 20(12), pp. 375:1-375:23, 2024.
[9] Shuo Chen, Jiaying Peng, Xiaolong Li, and Yao Zhao, “On the unstable convergence regime of gradient descent,” in Proc. AAAI, pp. 11373-11380, 2024.
[10] Mengyao Xiao, Xiaolong Li, Yao Zhao, Bin Ma, and Guodong Guo, “A novel reversible data hiding scheme based on pixel-residual histogram,” ACM TOMM, 19(1s), pp. 46:1-46:19, 2023.
[11] Xiaolong Liu, Yang Yu, Xiaolong Li, Yao Zhao, and Guodong Guo, “TCSD: Triple complementary streams detector for comprehensive deepfake detection,” ACM TOMM, 19(6), pp. 213:1-213:22, 2023.
[12] Yakun Niu, Xiaolong Li, Yao Zhao, and Rongrong Ni, “Detection of double JPEG compression with the same quantization matrix via convergence analysis,” IEEE TCSVT, 32(5), pp. 3279-3290, 2022.
[13] Wenjie Li, Xiaolong Li, Rongrong Ni, and Yao Zhao, “Quantization step estimation for JPEG image forensics,” IEEE TCSVT, 32(7), pp. 4816-4827, 2022.
[14] Qi Chang, Xiaolong Li, and Yao Zhao, “Reversible data hiding for color images based on adaptive three-dimensional histogram modification,” IEEE TCSVT, 32(9), pp. 5725-5735, 2022.
[15] Haorui Wu, Xiaolong Li, Xiangyang Luo, Xinpeng Zhang, and Yao Zhao, “General expansion-shifting model for reversible data hiding: Theoretical investigation and practical algorithm design,” IEEE TCSVT, 32(9), pp. 5989-6001, 2022.
[16] Qi Chang, Xiaolong Li, Yao Zhao, and Rongrong Ni, “Adaptive pairwise prediction-error expansion and multiple histograms modification for reversible data hiding,” IEEE TCSVT, 31(12), pp. 4850-4863, 2021.
[17] Mengyao Xiao, Xiaolong Li, Bin Ma, Xinpeng Zhang and Yao Zhao, “Efficient reversible data hiding for JPEG images with multiple histograms modification,” IEEE TCSVT, 31(7), pp. 2535-2546, 2021.
[18] Wenfa Qi, Xiaolong Li, Tong Zhang, and Zongming Guo, “Optimal reversible data hiding scheme based on multiple histograms modification,” IEEE TCSVT, 30(8), pp. 2300-2312, 2020.
[19] Xiang Wang, Xiaolong Li, and Qingqi Pei, “Independent embedding domain based two-stage robust reversible watermarking,” IEEE TCSVT, 30(8), pp. 2406-2417, 2020.
[20] Tong Zhang, Xiaolong Li, Wenfa Qi, and Zongming Guo, “Location-based PVO and adaptive pairwise modification for efficient reversible data hiding,” IEEE TIFS, 15, pp. 2306-2319, 2020.
[21] Zhipeng Chen, Benedetta Tondi, Xiaolong Li, Rongrong Ni, Yao Zhao, and Mauro Barni, “Secure detection of image manipulation by means of random feature selection,” IEEE TIFS, 14(9), pp. 2454-2469, 2019.
[22] Bo Ou, Xiaolong Li, Weiming Zhang, and Yao Zhao, “Improving pairwise PEE via hybrid-dimensional histogram generation and adaptive mapping selection,” IEEE TCSVT, 29(7), pp. 2176-2190, 2019.
[23] Yuanyuan Ma, Xiangyang Luo, Xiaolong Li, Zhenkun Bao, and Yi Zhang, “Selection of rich model steganalysis features based on decision rough set α-positive region reduction,” IEEE TCSVT, 29(2), pp. 336-350, 2019.
[24] Yunqing Shi, Xiaolong Li, Xinpeng Zhang, Haotian Wu, and Bin Ma, “Reversible data hiding: Advances in the past two decades,” IEEE Access, 4, pp. 3210-3237, 2016.
[25] Xiaolong Li, Weiming Zhang, Xinlu Gui, and Bin Yang, “Efficient reversible data hiding based on multiple histograms modification,” IEEE TIFS, 10(9), pp. 2016-2027, 2015.
[26] Bin Li, Ming Wang, Xiaolong Li, Shunquan Tan, and Jiwu Huang, “A strategy of clustering modification directions in spatial image steganography,” IEEE TIFS, 10(9), pp. 1905-1917, 2015.
[27] Xiaolong Li, Siren Cai, Weiming Zhang, and Bin Yang, “A further study of large payloads matrix embedding,” Information Sciences, 324, pp. 257-269, 2015.
[28] Xiaolong Li, Siren Cai, Weiming Zhang, and Bin Yang, “Matrix embedding in finite abelian group,” Signal Processing, 113, pp. 250-258, 2015.
[29] Bin Li, Tian-Tsong Ng, Xiaolong Li, Shunquan Tan, and Jiwu Huang, “Statistical model of JPEG noises and its application in quantization step estimation,” IEEE TIP, 24(5), pp. 1471-1484, 2015.
[30] Jian Li, Xiaolong Li, Bin Yang, and Xingming Sun, “Segmentation-based image copy-move forgery detection scheme,” IEEE TIFS, 10(3), pp. 507-518, 2015.
[31] Bin Li, Tian-Tsong Ng, Xiaolong Li, Shunquan Tan, and Jiwu Huang, “Revealing the trace of high-quality JPEG compression through quantization noise analysis,” IEEE TIFS, 10(3), pp. 558-573, 2015.
[32] Xiaocheng Hu, Weiming Zhang, Xiaolong Li, and Nenghai Yu, “Minimum rate prediction and optimized histograms modification for reversible data hiding,” IEEE TIFS, 10(3), pp. 653-664, 2015.
[33] Weiming Zhang, Xiaocheng Hu, Xiaolong Li, and Nenghai Yu, “Optimal transition probability of reversible data hiding for general distortion metrics and its applications,” IEEE TIP, 24(1), pp. 294-304, 2015.
[34] Bo Ou, Xiaolong Li, Yao Zhao, Rongrong Ni, and Yunqing Shi, “Pairwise prediction-error expansion for efficient reversible data hiding,” IEEE TIP, 22(12), pp. 5010-5021, 2013.
[35] Xiaolong Li, Bin Li, Xiangyang Luo, Bin Yang, and Ruihui Zhu, “Steganalysis of a PVD-based content adaptive image steganography,” Signal Processing, 93(9), pp. 2529-2538, 2013.
[36] Xiaolong Li, Weiming Zhang, Xinlu Gui, and Bin Yang, “A novel reversible data hiding scheme based on two-dimensional difference-histogram modification,” IEEE TIFS, 8(7), pp. 1091-1100, 2013.
[37] Weiming Zhang, Xiaocheng Hu, Xiaolong Li, and Nenghai Yu, “Recursive histogram modification: Establishing equivalency between reversible data hiding and lossless data compression,” IEEE TIP, 22(7), pp. 2775-2785, 2013.
[38] Xiaolong Li, Bin Li, Bin Yang, and Tieyong Zeng, “General framework to histogram-shifting-based reversible data hiding,” IEEE TIP, 22(6), pp. 2181-2191, 2013.
[39] Xiaolong Li, Jian Li, Bin Li, and Bin Yang, “High-fidelity reversible data hiding scheme based on pixel-value-ordering and prediction-error expansion,” Signal Processing, 93(1), pp. 198-205, 2013.
[40] Xiaolong Li, Bin Yang, and Tieyong Zeng, “Efficient reversible watermarking based on adaptive prediction-error expansion and pixel selection,” IEEE TIP, 20(12), pp. 3524-3533, 2011.
[41] Xiaolong Li, Bin Yang, Daofang Cheng, and Tieyong Zeng, “A generalization of LSB matching,” IEEE SPL, 16(2), pp. 69-72, 2009.




专著/译著

专利

[1]  亓文法，李晓龙，张华，一种数字水印嵌入与提取方法及装置，2006.10.25，中国，ZL200610114048.0

[2]  亓文法，李晓龙，一种用于数字图像的数字水印方法及装置，2007.01.10，中国，ZL 200710063389.4

[3]  李晓龙，亓文法，程道放，基于数字图像变换域系数统计模型的水印嵌入及提取方法，2007.01.25，中国，ZL 200710063043.4

[4]  李晓龙，亓文法，杨斌，张华，程道放，二值图像中数字水印的嵌入、提取方法和装置，2007.09.11，中国，ZL 200710121642.7

[5]  李晓龙，亓文法，程道放，杨斌，一种数字图像的水印嵌入、提取方法及装置，2007.09.12，中国，ZL 200710121700.6

[6]  李晓龙，杨斌，程道放，亓文法，一种在数字图像中嵌入和提取水印的方法与装置，2007.12.27，中国，ZL 200710304442.5

[7]  李晓龙，亓文法，程道放，杨斌，二值文本图像中数字水印的嵌入和提取的方法及装置，2008.01.08，中国，ZL 200810055770.0

[8]  王祥，郭宗明，李晓龙，杨斌，一种数字水印嵌入和提取方法及装置，2009.10.19，中国，ZL 200910236058.5

[9]  王高阳，亓文法，李晓龙，杨斌，一种数字图像中水印嵌入和检测的方法及装置，2009.12.31，中国，ZL 200910217512.2

[10] 郭宗明，王祥，李晓龙，杨斌，可逆水印嵌入、提取方法及装置和图像恢复方法及装置，2010.03.15，中国，ZL 201010126034.7

[11] 王超，李晓龙，亓文法，杨斌，一种数字图像中可逆水印的嵌入方法及其提取方法，2010.04.23，中国，ZL 201010159959.1

[12] 李晓龙，王超，亓文法，杨斌，一种数字图像中的水印嵌入和提取方法，2010.06.22，中国，ZL 201010215767.8

软件著作权

获奖与荣誉

2015，视觉媒体内容保护的理论与方法，教育部自然科学二等奖（排名第三）

2022，数字图像内容安全与保护关键理论研究，山东省自然科学二等奖（排名第二）

2023，‌信息隐藏的基础理论与方法，河南省自然科学一等奖（排名第二）

2023，数字资产权益保护关键技术研究与应用，上海市科技进步二等奖（排名第三）

社会兼职