學院消息

Title：

Attack as the Best Defense: Improving the Model Robustness via Adversarial Training

Time & Venue：

November 16 (Wed) 2022, 15:30-16:30

https://teams.live.com/meet/9513389228919

Speaker：

Hong-Han Shuai

Hong-Han Shuai received the B.S. degree from the Department of Electrical Engineering, National Taiwan University (NTU), Taipei, Taiwan, R.O.C., in 2007, the M.S. degree in Computer Science from NTU in 2009, and the Ph.D. degree from Graduate Institute of Communication Engineering, NTU, in 2015. He is now an associate professor in NCTU. His research interests are in the area of multimedia processing, machine learning, social network analysis, and data mining. His works have appeared in top-tier conferences such as MM, CVPR, AAAI, KDD, WWW, ICDM, CIKM and VLDB, and top-tier journals such as TKDE, TMM and JIOT. Moreover, he has served as the PC member for international conferences including MM, AAAI, IJCAI, WWW, and the invited reviewer for journals including TKDE, TMM, JVCI, and JIOT.

Outline：

With the advance of deep learning, learning-based approaches have been applied to different fields and achieved a great success. However, deep learning models are vulnerable to attacks. In this talk, I will introduce several works aiming to attack deep learning models and several defense mechanisms. Finally, I will introduce one of my paper that uses adversarial attack as defense to prevent malicious image-to-image translation models.