讲座主题：
Generative Adversarial Networks for Privacy-Preserving Data Publishing
主讲人姓名及介绍：
Dr. Zhipeng Cai received his PhD and MS degrees in the Department of Computing Science at University of Alberta, and BS degree from the Department of Computer Science and Engineering at Beijing Institute of Technology. Dr. Cai is currently a Professor in the Department of Computer Science and the College of Business at Georgia State University. Dr. Cai’s research areas focus on Machine learning, Internet of Things, Privacy, and Big data. Dr. Cai is the recipient of an NSF CAREER Award. Dr. Cai's research has been supported by the National Science Foundation, the U.S. Department of State, and other academic and industrial sponsors. Dr. Cai has published more than 100 papers in top journals and conferences including more than 70 IEEE/ACM Transactions papers. His publications have been cited for more than 11000 times. Dr. Cai is the Editor-in-Chief for Wireless Communications and Mobile Computing and Associate Editor-in-Chief for Elsevier High-Confidence Computing Journal. He serves as an editor for several prestigious journals including IEEE Transactions on Knowledge and Data Engineering (TKDE), IEEE Transactions on Vehicular Technology (TVT), IEEE Transactions on Wireless Communications (TWC), IEEE Transactions on Computational Social Systems (TCSS), IEEE Internet of Things Journal, etc. Dr. Cai is a Steering Committee Co-Chair for the international conferences of WASA, IPCCC and COCOON. He has served as a General/Program Chair for many international conferences such as ICDCS, SocialCom, ISBRA, etc.
蔡志鹏博士在阿尔伯塔大学计算科学系获得博士和硕士学位，并在北京理工大学计算机科学与工程系获得学士学位。蔡博士目前是佐治亚州立大学计算机科学系和商学院的教授。蔡博士的研究领域集中于机器学习、物联网、隐私和大数据。蔡博士是美国国家科学基金会职业奖的获得者。蔡博士的研究得到了国家科学基金会、美国国务院以及其他学术和工业赞助者的支持。蔡博士在顶级期刊和会议上发表了100多篇论文，包括70多篇IEEE/ACM交易论文。他的著作被引用了11000多次。蔡博士是《无线通信和移动计算》的总编辑，也是《Elsevier High-Confidence Computing Journal》的副总编辑。他担任多家著名杂志的编辑，包括IEEE知识与数据工程学报（TKDE）、IEEE车辆技术学报（TVT）、IEEE无线通信学报（TWC）、IEEE计算社会系统学报（TCSS）、IEEE物联网杂志、，蔡博士是WASA、IPCCC和COCOON国际会议的指导委员会联合主席。他曾担任ICDC、SocialCom、ISBRA等多个国际会议的综合/项目主席。
报告摘要：
Generative Adversarial Networks (GANs) are widely applied to estimate a density function over an unknown data-generating distribution. A variety of GAN models have been proposed to improve the performance of data publication, data management, knowledge discovery, information fusion, etc. Besides benefit, GAN also bring unique challenges to people, among which privacy issues are extremely urgent yet intractable concerns to be extensively investigated. In this talk, we will introduce three novel GAN models in cybersecurity domain, including Seed Free Graph De-anonymization, Privacy Graph Embedding Data Publication and Generative Adversarial Networks for Auto-Driving Vehicles. The results of extensive real-data experiments validate the superiority of our proposed models.
生成性对抗网络（GANs）广泛应用于估计未知数据生成分布上的密度函数。为了提高数据发布、数据管理、知识发现、信息融合等方面的性能，人们提出了各种各样的GAN模型。除了带来好处之外，GAN还给人们带来了独特的挑战，其中隐私问题是极其紧迫但棘手的问题，需要进行广泛的研究。在本次演讲中，我们将介绍网络安全领域的三种新的GAN模型，包括无种子图去匿名化、隐私图嵌入数据发布和自动驾驶车辆生成对抗网络。大量的实际数据实验结果验证了我们提出的模型的优越性。
