李斌 Dr. Bin Li
教授,特聘研究员,博士生导师
广东省智能信息处理重点实验室主任,深圳市媒体信息内容安全重点实验室主任
Professor, Research Fellow, PhD. Supervisor
Director of Guangdong Key Lab of Intelligent Information Processing
Director of Shenzhen Key Lab of Media Security
联系方式(Contact):
招聘博士后/专职研究人员(年薪33万起,根据研究方向匹配程度可达40-50万)
实验室主页:http://media-sec.szu.edu.cn/view/libin105.html
Email: libin [AT] szu.edu.cn
Tel: 0755-22673509
地址:深圳市南山区白石路澳门3044永利N801
Address: Room N801, College of Electronics and Information Engineering, Shenzhen University
简介(Biography):
教授,博导,广东省自然科学基金杰出青年基金获得者,深圳市高层次专业人才,深圳市优秀教师,IEEE/CCF/CSIG高级会员,我校新锐研究生导师,入选全球前2%顶尖科学家榜单。获中山大学通信工程专业学士学位,通信与信息系统专业博士学位,美国新泽西理工学院联合培养博士。现担任广东省智能信息处理重点实验室主任、深圳市媒体信息内容安全重点实验室主任、广东省图象图形学会副理事长。
研究领域包括人工智能、多媒体处理、信息安全等。发表包括国际权威刊物IEEE T-IFS、IEEE T-IP、IEEE T-CSVT等SCI/EI论文150多篇,编著教材2部,谷歌学术引用6000多次,H指数34,i-10指数59。获国家发明专利授权10余项,美国专利授权2项,转化专利1项,软件著作权8项,参与制定技术标准2件。获中国计算机学会科学技术奖自然科学一等奖、深圳市自然科学二等奖。主持国家自然科学基金、深圳市学科布局等科研项目。担任IEEE T-IFS (Transactions on Information Forensics and Security)、OJ-SP (Open Journal of Signal Processing)期刊编委。
Dr. BIN LI received the B.E. degree in communication engineering and the Ph.D. degree in communication and information system from Sun Yat-sen University, Guangzhou, China, in 2004 and 2009, respectively. He was a Visiting Scholar with the New Jersey Institute of Technology, Newark, NJ, USA, from 2007 to 2008. In 2009, he joined Shenzhen University, Shenzhen, China, where he is currently a professor. He is the Director of Guangdong Key Laboratory of Intelligent Information Processing and the Director of Shenzhen Key Laboratory of Media Security. His current research interests include image processing, multimedia forensics, and pattern recognition.
招生与招聘 (Recruitment):
学硕/学博/博士后:信息与通信工程。
专硕/专博:新一代电子信息技术
本科生:欢迎优秀大二、大三学生参与科研项目
招收对人工智能(机器学习)、多媒体处理、信息安全等研究方向感兴趣,态度认真,勤奋刻苦的学生。提供良好的科研学术环境,表现优秀者可推荐到国外著名大学培养。已毕业学生主要在互联网头部企业、上市公司等从事人工智能、图像处理、算法研发等工作。
招聘博士后/专职研究人员(年薪33万起,根据研究方向匹配程度可达40-50万)
1. 招聘研究方向(包括但不限于):机器学习(包括深度学习)、图像/音频/视频处理与分析、计算机视觉、信息安全。
2. 岗位职责:
1)撰写发表IEEE Trans/CCF A类级别学术论文;
2)与合作导师共同承担重要的科研课题,按计划完成博士后入站期间的科研任务;
3)协助团队及实验室建设工作。
3. 应聘条件:
1) 年龄在35周岁以下、获得博士学位不超过3年;
2)具有良好的学术道德和严谨科学态度、身体健康、能胜任岗位的工作要求;
3)具有较好的编程、英语阅读和写作能力。
4. 应聘流程:
1) 将个人简历发给libin【AT】szu.edu.cn;
2) 经过初筛后进行面试;
3) 在面试结束后经学校审批后再通知是否同意聘用。
招聘方会对申请人递交的应聘材料予以保密。
获得奖励(Awards) :
1)科研奖励
· 图像隐写安全关键技术.广东省计算机学会科学技术奖自然科学二等奖(1/5). 2023.2
· 自适应信息隐写安全理论与方法.深圳市自然科学二等奖(1/5).2022.5
· 信息隐藏理论与方法,CCF科学技术奖自然科学一等奖(3/5),2019.10
· 郑铿涛,李斌*,曾锦华.应用注意力机制的文档图像篡改与脱敏定位. 第三届CSIG媒体取证与安全大会优秀论文奖.2022.11
· 陈晓铭,李斌*. 应用双通道Faster R-CNN与注意力机制模型的图像篡改检测. 第二十届全国图象图形学学术会议(NCIG2020), 2020.6 (最佳论文奖)
· Yuankun Huang, Shunquan Tan, Bin Li*, Jiwu Huang. VPCID—A VoIP Phone Call Identification Database. International Workshop on Digital Forensics and Watermarking , 11378: 307-321, 2018.10 (Best Paper)
· Ming Wang, Bin Li*, Shunquan Tan, Xiaolong Li. A Spatial Steganographic Method Employing the Strategy of Clustering Modification Directions. 第十二届全国信息隐藏暨多媒体信息安全大会优秀论文奖. 中国电子学会通信学分会. 2015.3
2)教学奖励
· 深圳市优秀教师.2019.9
· 本科教学突出贡献奖. 2022.7
· 腾讯优秀教学管理团队奖.2023.6
· 我校优秀本科课程奖.2023.4
· 百篇优秀硕士学位论文指导教师.2023.7
· 百篇优秀本科毕业论文指导教师.2019.7
· 《概率论与数理统计》.首届全国地方高校优课联盟品牌MOOC. 2016.11
· 优秀毕业研究生指导教师(学生:王明、陈涵、余泽钦)
3)学生竞赛(指导教师)
· 盘古石杯全国电子数据取证大赛,三等奖,2023.7
· IJCB2022-DFGC深度伪造博弈比赛检测赛道,冠军,2022.9
· CSIG图像图形技术挑战赛(行为识别大赛),华为优胜奖,2022.8
· 第二届中国移动“梧桐杯”大数据应用创新大赛,优秀奖,2022.8
· 第九届CCF大数据与计算智能大赛(CCF-BDCI),二等奖,2022.1
· 荔园挑战创新创业大赛,一等奖,2021.12
· IJCB2021-DFGC深度伪造博弈比赛检测赛道,冠军,2021.8
· 中国高校计算机大赛——大数据挑战赛,一等奖,2019.9
· 第十二届中国计算机设计大赛,二等奖,2019.7
· 挑战杯大学生课外学术科技作品竞赛,三等奖,2018.12
代表性学术论文
[27] Weixiang Li, Bin Li*, Weiming Zhang, Shengli Zhang. Quaternary Quantized Gaussian Modulation with Optimal Polarity Map Selection for JPEG Steganography. IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2023. (中科院大类一区,TOP期刊,CCF A类,安全领域顶级期刊)
[26] Weixiang Li, Shihang Wu, Bin Li*, Weixuan Tang, Xinpeng Zhang. Payload-Independent Direct Cost Learning for Image Steganography. IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2023. (中科院大类一区,TOP期刊,多媒体领域顶级期刊)
[25] Shunquan Tan, Qiushi Li, Laiyuan Li, Bin Li, Jiwu Huang. STD-NET: Search of Image Steganalytic Deep-Learning Architecture via Hierarchical Tensor Decomposition. IEEE Transactions on Dependable and Secure Computing (IEEE TDSC), 2023. (中科院大类二区,TOP期刊,CCF A类,安全领域顶级期刊)
[24] Xianbo Mo, Shunquan Tan, Weixuan Tang, Bin Li, Jiwu Huang. ReLOAD: Using Reinforcement Learning to Optimize Asymmetric Distortion for Additive Steganography. IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2023. (中科院大类一区,TOP期刊,CCF A类,安全领域顶级期刊)
[23] Weixuan Tang, Bin Li*, Weixiang Li, Yuangen Wang, Jiwu Huang. Reinforcement Learning of Non-additive Joint Steganographic Embedding Costs with Attention Mechanism. Science China-Information Sciences, 2023. (中科院大类二区,CCF T1类,国内计算领域高质量科技期刊)
[22] Han Chen, Yuezun Li, Dongdong Lin, Bin Li*, Junqiang Wu. Watching the BiG Artifacts: Exposing DeepFake Videos via Bi-Granularity Artifacts. Pattern Recognition, 2023. (中科院大类一区,TOP期刊,人工智能领域权威期刊)
[21] Han Chen, Yuzhen Lin, Bin Li*, Shunquan Tan. Learning Features of Intra-consistency and Inter-diversity: Keys towards Generalizable Deepfake Detection. IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2023. (中科院大类一区,TOP期刊,多媒体领域顶级期刊)
[20] Guanglin Li, Bin Li*, Shunquan Tan, Guoping Qiu. Learning Deep Co-occurrence Features. IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2023. (中科院大类一区,TOP期刊,多媒体领域顶级期刊)
[19] Weixuan Tang, Bin Li*, Mauro Barni, Jin Li, Jiwu Huang. Improving Cost Learning for JPEG Steganography by Exploiting JPEG Domain Knowledge. IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2022. (中科院大类一区,TOP期刊,多媒体领域顶级期刊)
[18] Xinghong Qin, Bin Li*, Shunquan Tan, Weixuan Tang, Jiwu Huang. Gradually Enhanced Adversarial Perturbations on Color Pixel Vectors for Image Steganography. IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2022. (中科院大类一区,TOP期刊,多媒体领域顶级期刊)
[17] Long Zhuo, Shunquan Tan, Bin Li, Jiwu Huang. Self-Adversarial Training Incorporating Forgery Attention for Image Forgery Localization. IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2022. (中科院大类一区,TOP期刊,CCF A类,安全领域顶级期刊)
[16] Qiushi Li, Shengda Chen, Shunquan Tan, Bin Li, Jiwu Huang. One-Class Double Compression Detection of Advanced Videos Based on Simple Gaussian Distribution Model. IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2022. (中科院大类一区,TOP期刊,多媒体领域顶级期刊)
[15] Weixuan Tang, Bin Li*, Mauro Barni, Jin Li and Jiwu Huang. An Automatic Cost Learning Framework for Image Steganography Using Deep Reinforcement Learning. IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2021. (中科院大类一区,TOP期刊,CCF A类,安全领域顶级期刊)
[14] Shunquan Tan, Weilong Wu. Zilong Shao, Qiushi Li, Bin Li, Jiwu Huang. CALPA-NET: Channel-Pruning-Assisted Deep Residual Network for Steganalysis of Digital Images. IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2020. (中科院大类一区,TOP期刊,CCF A类,安全领域顶级期刊)
[14] Xin Liao, Yingbo Yu, Bin Li, Zhongpeng Li, Zheng Qin. A New Payload Partition Strategy in Color Image Steganography. IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2020. (中科院大类一区,TOP期刊,多媒体领域顶级期刊)
[13] Yuankun Huang, Bin Li*, Mauro Barni, Jiwu Huang. Identification of VoIP Speech with Multiple Domain Deep Features. IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2019. (中科院大类一区,TOP期刊,CCF A类,安全领域顶级期刊)
[12] WeixuanTang, Bin Li*, Shunquan Tan, Mauro Barni, Jiwu Huang. CNN-based Adversarial Embedding for Image Steganography. IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2019. (中科院大类一区,TOP期刊,CCF A类,安全领域顶级期刊)
[11] Xinghao Jiang, Qiang Xu, Tanfeng Sun, Bin Li, Peisong He. Detection of HEVC Double Compression With the Same Coding Parameters Based on Analysis of Intra Coding Quality Degradation Process. IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2019. (中科院大类一区,TOP期刊,CCF A类,安全领域顶级期刊)
[10] Bin Li, Zhongpeng Li, Shijun Zhou, Shunquan Tan, Xiaoling Zhang. New Steganalytic Features for Spatial Image Steganography based on Derivative Filters and Threshold LBP Operator. IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2017. (中科院大类一区,TOP期刊,CCF A类,安全领域顶级期刊)
[9] Shunquan Tan, Haojie Zhang, Bin Li, Jiwu Huang. Pixel-Decimation-Assisted Steganalysis of Synchronize-Embedding-Changes Steganography. IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2017. (中科院大类二区,CCF A类,安全领域顶级期刊)
[8] Jishen Zeng, Shunquan Tan, Bin Li, Jiwu Huang. Large-scale JPEG image steganalysis using hybrid deep-learning framework. IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2017. (中科院大类二区,CCF A类,安全领域顶级期刊)
[7] Da Luo, Rui Yang, Bin Li and Jiw Huang, Detection of Double Compressed AMR Audio Using Stacked Autoencoder. IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2016. (中科院大类二区,CCF A类,安全领域顶级期刊)
[6] Shengda Chen, Shunquan Tan, Bin Li, Jiwu Huang. Automatic Detection of Object-based Forgery in Advanced Video. IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2016. (中科院大类二区,多媒体领域顶级期刊)
[5] Bin Li, Ming Wang, Xiaolong Li, Shunquan Tan, Jiwu Huang. A Strategy of Clustering Modification Directions in Spatial Image Steganography. IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2015. (中科院大类二区,CCF A类,安全领域顶级期刊)
[4] Bin Li, Tian-Tsong Ng, Xiaolong Li, Shunquan Tan, Jiwu Huang. Statistical Model of JPEG Noises and Its Application in Quantization Step Estimation. IEEE Transactions on Image Processing (IEEE TIP), 2015. (中科院大类一区,CCF A类,多媒体领域顶级期刊)
[3] Bin Li, Tian-Tsong Ng, Xiaolong Li, Shunquan Tan, Jiwu Huang. Revealing the Trace of High-Quality JPEG Compression through Quantization Noise Analysis. IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2015. (中科院大类二区,CCF A类,安全领域顶级期刊)
[2] Bin Li, Shunquan Tan, Ming Wang, Jiwu Huang. Investigation on cost assignment in spatial image steganography. IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2014. (中科院大类二区,CCF A类,安全领域顶级期刊)
[1] Xiaolong Li, Bin Li, Bin Yang, General framework to histogram-shifting based reversible data hiding. IEEE Transactions on Image Processing (IEEE TIP), 2013. (中科院大类一区,CCF A类,多媒体领域顶级期刊)
科研项目 (Research Projects):
· 国家自然科学基金联合基金项目,可跨域少样本学习的隐写分析网络研究(U22B2047),2023.01-2026.12,我校课题组负责人
· 国家自然科学基金面上项目,对抗环境下基于深度学习的JPEG图像取证与反取证研究(61872244),2019.01-2022.12,主持
· 国家自然科学基金面上项目,非加性失真图像隐写研究(61572329),2016.01-2019.12,主持
· 国家自然科学基金青年基金项目,特征向量变化可控的安全隐写研究(61103174),2012.01-2014.12,主持
· 广东省自然科学基金杰出青年项目,AI生成型虚假视听媒体取证技术研究(2019B151502001),2019.10-2023.9,主持
· 广东省自然科学基金项目,基于量化噪声和深度架构的JPEG图像篡改检测(2014A030313557),2015.01-2018.01,主持
· 深圳市基础研究重点项目,AI伪造图像音视频检测理论与关键技术研究(JCYJ20200109105008228),2020.11-2023.10,主持
· 深圳市基础研究项目,基于深度神经网络的图像修复关键技术(JCYJ20180305124325555),2019.01-2020.12,主持
· 深圳市战略性新兴产业发展专项资金项目,数字可视媒体内容篡改盲取证的关键技术研究(JCYJ20120613113535357),2012.08-2014.08,主持