On the afternoon of June 23, 2023, Professor Zhang Weiming, Deputy Dean of the School of Cybersecurity at the University of Science and Technology of China, was invited to give an academic lecture titled "Deep Forgery Defense Methods Driven by Generative Capability". The lecture was hosted by Professor Jia Wei, and more than 30 teachers and students from the college attended the lecture. 

This lecture focused on deep video forgery and detection, introduced effective detection techniques for unknown forgery algorithms in asymmetric adversarial environments, reported the latest achievements of his research team in the field of deep video forgery detection, especially the recent application achievements in high-fidelity digital human restoration and its important impact, and further revealed the opportunities and challenges brought by large language models and the underlying mathematical theories. During the interactive part of the lecture, Professor Zhang had a friendly exchange with the teachers and students present, discussed the technical details of deep video forgery detection and large language model watermarking, shared his insights and experiences on how to maintain enthusiasm and motivation for scientific research, and answered the students' related doubts during their learning process.

This report has promoted the exchange and cooperation between the University of Science and Technology of China and Hefei University of Technology in the field of deep video forgery detection, providing important inspiration and reference for our teachers and students to engage in related research work.

Introduction of the speaker: Zhang Weiming, Deputy Dean, Professor, and Doctoral Supervisor of the School of Cyber Security at the University of Science and Technology of China. His main research interests include information hiding and artificial intelligence security. He has published more than 200 papers in internationally renowned academic journals and conferences such as IEEE TIT, TPAMI, TIFS, TIP, CVPR, S&P, ICCV, NeurIPS, AAAI, etc. He has presided over more than 20 projects such as the National Natural Science Foundation Key, National Key R&D Topics, National 863, etc. He has won the first prize of the Military Science and Technology Progress Award, the first prize of the Anhui Province Natural Science Award, the special prize of the Anhui Province Teaching Achievement Award, and the ACM SIGSOFT Outstanding Paper Award. He led the team to develop the most influential online face deep synthesis open source tool DeepFaceLab, with a total download of over 120,000 times, and was selected as one of the top ten popular projects on GitHub2020 along with OpenAI's GPT-2 project; participated in the world's largest "Deep Forgery Detection Challenge (DFDC)" organized by Facebook, MIT, etc., won the runner-up (a prize of 300,000 US dollars), and was rated as one of the eight Chinese innovation achievements in the field of artificial intelligence security since 2014 by the China Academy of Information and Communications Technology. He was selected as one of the top ten outstanding figures in artificial intelligence in the Yangtze River Delta in 2021.