Speakers

Professor Yiu-ming Cheung

 IEEE Fellow, AAAS Fellow, IET Fellow, AAIA Fellow, and British Computer Society (BCS) Fellow

Hong Kong Baptist University (HKBU), China

Biography: 

Yiu-ming Cheung is currently a Chair Professor (Artificial Intelligence) of the Department of Computer Science, Dean of Institute for Research and Continuing Education (IRACE), and Associate Director of Institute of Computational and Theoretical Studies in Hong Kong Baptist University (HKBU). He received PhD degree from Department of Computer Science and Engineering at The Chinese University of Hong Kong in 2000, and then joined the Department of Computer Science at HKBU in 2001. He is an IEEE Fellow, AAAS Fellow, IAPR Fellow, IET Fellow, and British Computer Society (BCS) Fellow. He is the awardee of RGC Senior Research Fellow with receiving a fellowship grant of HK$7.8 million over a period of 60 months. Since 2019, he has been ranked the World’s Top 1% Most-cited Scientists in the field of Artificial Intelligence and Image Processing by Stanford University for six consecutive years. Furthermore, he has been elected as a Distinguished Lecturer of IEEE Computational Intelligence Society, and named a Chair Professor of Changjiang Scholars Program by the Ministry of Education of the People’s Republic of China for the dedication and exceptional achievements in his academic career. In addition, he is serving as the Editor-in-Chief of IEEE Transactions on Emerging Topics in Computational Intelligence.

His research interests include machine learning and visual computing, as well as their applications in data science, pattern recognition, multi-objective optimization, and information security. He has published over 300 articles in the high-quality conferences and journals, including TPAMI, TNNLS, TIFS, TIP, TMM, TKDE, TCYB, CVPR, ICML, IJCAI, AAAI, and so on. His four co-authored papers have been selected as ESI Highly Cited Papers (i.e. listed in Top 1% globally in the corresponding discipline). Moreover, he has been granted one Chinese patent and two US patents. Subsequently, the underlying technique of his eye-gaze tracking patent has been successfully applied to develop the first mobile app for fatigue driving detection. It turns out that, selected from 1000 new inventions and products of 700+ competition teams from 40 countries, he was awarded two most prestigious prizes: (1) the Gold Medal with Distinction (i.e. the highest grade in Gold Medals) and (2) Swiss Automobile Club Prize, in the 45th International Exhibition of Invention, Geneva, Switzerland, on March 29-April 2, 2017, in recognition of his innovative work. Also, he was the Gold Award Winner of Hong Kong Innovative Invention Award in the Seventh Hong Kong Innovative Technologies Achievement Award 2017. In addition, he won the Gold Medal with Congratulations of Jury (i.e. the highest grade in Gold Medals) and the Award of Excellence from Romania, respectively, at the 46th International Exhibition of Inventions of Geneva 2018 with his invention “Lip-password: Double Security System for Identity Authentication”, and received HKBU Innovation Award 2024. He is the recipient of: (1) President’s Award for Outstanding Performance in Scholarly Work 2023-2024, (2) 2023 APNNS Outstanding Achievement Award, (3) 2017 IETI Annual Scientific Award, and (4) 2017-2019 Albert Nelson Marquis Lifetime Achievement Award. Besides, he was the recipient of: (1) Research Excellence Paper Award 2022-23 of Faculty of Science at HKBU, (2) The Best Paper Award (Second Prize) of Computer Academy of Guangdong, (3) Best Research Award of Department of Computer Science at HKBU in 2011 and 2021, respectively, (4) Best in Theoretical Paper Award in WI-IAT’2020, (5) Best Paper Awards in DOCS’2024, SEAL’2017, ISICA’2017, ICNC-FSKD’2014, and IEEE IWDVT’2005, respectively, and (6)  Best Student Paper Award in ISMIS’2018.

He was the Founding Chairman of IEEE (Hong Kong) Computational Intelligence Chapter and the Chair (2018-2022) of Technical Community on Intelligent Informatics (TCII) of IEEE Computer Society. He has served in various capacities (e.g., Organizing Committee Chair, Program Committee Chair, Program Committee Area Chair, and Financial Chair) at several top-tier international conferences, including IJCAI’2021, ICPR’2020, ICDM’2017 & 2018, WCCI’2016, WI-IAT’2012, ICDM’2006 & WI-IAT’2006, to name a few. He has been served as an Associate Editor for several prestigious journals, including IEEE Transactions on Cybernetics (2018-2023), IEEE Transactions on Cognitive and Developmental Systems, IEEE Transactions on Neural Networks and Learning Systems (2014-2020), ACM Transactions on Intelligent Systems and Technology, Pattern Recognition, Pattern Recognition Letters (2022-2024), Knowledge and Information Systems (KAIS), and Neurocomputing, as well as the Guest Editor in several international journals. Currently, he is an Engineering Panel member of Research Grants Council, Hong Kong, and a member of assessment panel of Enterprise Support Scheme (ESS) under the Innovation and Technology Fund (ITF). Also, he is a member of Fellow Evaluation Committee of IEEE Computer Society and IEEE Computational Intelligence Society, respectively.

Professor Jian Huang

Huazhong University of Science and Technology, China

Biography: 

Huang Jian, a full professor at Huazhong University of Science and Technology, serves as the head of the Department of Intelligent Science and Technology in the School of Artificial Intelligence and Automation, and the director of the Hubei Key Laboratory of Brain-inspired Intelligent Systems. He has been selected as a leading talent in scientific and technological innovation under the National Special Support Program for High-Level Talents and supported by the Ministry of Education's "New Century Excellent Talent Support Plan," receiving funding from the Hubei Provincial Natural Science Foundation's Distinguished Young Scholars Program. He holds positions such as the chairman of the IEEE Computational Intelligence Society Wuhan Chapter, vice-chairman of the Wuhan Automation Society, and vice-chairman of the Intelligent Robotics Professional Committee of the China Artificial Intelligence Society. He has previously served as a visiting professor at Nagoya University in Japan, a visiting professor at Université Paris-Est-Créteil Val de Marne in France, and a JSPS Fellow funded by the Japan Society for the Promotion of Science.

Professor Huang has led over twenty significant national and provincial-level research projects, including key projects of the National Key Research and Development Program of China, National Natural Science Foundation of China, International Cooperation Key Projects of the Ministry of Science and Technology, and Hubei Province Major Technology Innovation Projects. He has published over 120 SCI-indexed journal articles and has been cited more than 6,000 times on Google Scholar. He holds over 30 national invention patents, one U.S. invention patent, and one Japanese invention patent. His research achievements have been awarded one provincial-level science and technology grand prize (first place), three first-class awards, and one gold and one silver medal at the Geneva International Exhibition of Inventions.

Professor Huang also serves as an editorial board member for internationally renowned journals such as IEEE Transactions on Fuzzy Systems and IEEE Transactions on Automation Science and Engineering.

Yuqi Chen

ShanghaiTech University, China

Biography: 

Yuqi Chen is an assistant Professor (tenure-track) at School of Information Science and Technology in the ShanghaiTech University. Yuqi completed his Ph.D. in 2019 at the Singapore University of Technology and Design (SUTD) under the supervision of Sun Jun. Besides, he also collaborated closely with Chris Poskitt. From 2019 to 2021, he worked as a Research Scientist in the System Analysis and Verification (SAV) group at Singapore Management University(SMU).

Speech Title:Efficient Detection of Toxic Prompts in Large Language Models 

Abstract:Large languagemodels (LLMs) like ChatGPT and Gemini have significantly advanced natural language processing, enabling various applications such as chatbots and automated content generation. However, these models can be exploited by malicious individuals who craft toxic prompts to elicit harmful or unethical responses. These individuals often employ jailbreaking techniques to bypass safety mechanisms, highlighting the need for robust toxic prompt detection methods. Existing detection techniques, both blackbox and whitebox, face challenges related to the diversity of toxic prompts, scalability, and computational efficiency. In response, we propose ToxicDetector, a lightweight greybox method designed to efficiently detect toxic prompts in LLMs. ToxicDetector leverages LLMs to create toxic concept prompts, uses embedding vectors to form feature vectors, and employs a Multi-Layer Perceptron (MLP) classifier for prompt classification. Our evaluation on various versions of the LLama models, Gemma-2, and multiple datasets demonstrates that ToxicDetector achieves a high accuracy of 96.39% and a low false positive rate of 2.00%, outperforming state-of-the-art methods. Additionally, ToxicDetector’s processing time of 0.0780 seconds per prompt makes it highly suitable for real-time applications. ToxicDetector achieves high accuracy, efficiency, and scalability, making it a practical method for toxic prompt detection in LLMs.