News

RCPST Hosts its First Distinguished Lecture by Professor Xiang Yang

The RCPST Distinguished Lecture Series was successfully held on 21 November 2024, featuring an insightful presentation by IEEE Fellow Prof. Yang Xiang, Director of the Digital Capability Research Platform at Swinburne University of Technology, Australia. The event was hosted by Professor Haibo Hu, Director of RCPST and Associate Head of the Department of Electrical and Electronic Engineering at PolyU. His opening remarks set the stage for a thought-provoking session on the critical topic of AI security. Prof. Xiang delivered a distinguished lecture titled "Securing AI Systems: From Development to Deployment." He began by emphasizing the rapid advancements in artificial intelligence (AI) systems, which have become integral to numerous applications. This integration underscores the urgent need for innovative security measures to protect these systems throughout their lifecycle. Prof. Xiang highlighted that, despite their high accuracy, AI models are inherently vulnerable to a range of sophisticated attacks, posing significant risks to their security and trustworthiness. He stressed the importance of addressing the comprehensive security challenges faced by AI systems from their development phase through to deployment. Following this introduction, Prof. Xiang delved into the advanced defensive methods developed by his research team. These methods are designed to detect and neutralize sophisticated backdoor attacks that threaten the integrity of AI systems during their development. He also presented findings on the vulnerabilities of video classification systems, introducing a novel adversarial attack that underscores the threats to AI model availability during deployment. To conclude the lecture, Prof. Xiang offered valuable advice on the accountability of AI code generators from both development and deployment perspectives. His insights provided a comprehensive understanding of how to ensure accountability throughout the AI system lifecycle, emphasizing the need for robust security frameworks and ethical considerations in AI development. The lecture was followed by an engaging Q&A session, where attendees had the opportunity to discuss these pressing issues further with Prof. Xiang. On behalf of the RCPST, Prof. Hu then presented Prof. Xiang with a souvenir to express gratitude for his valuable contribution to the lecture series and his insights into the critical field of AI security.  The event was a resounding success, leaving participants with a deeper understanding of the complexities involved in securing AI systems and the innovative solutions being developed to address these challenges.  

Prof. Hu Secured Multimillion-dollar ITF project on Large Language Model Privacy

Prof. Hu has secured an ITF ITSP research grant of 2 million Hong Kong Dollars with title “MyGPTShield: A Personalized Privacy-Preserving Prompt Service for Large Generative AI Models”. Thanks to the booming of AI and cloud computing industry, generative AI has become increasingly popular and fostered new businesses opportunities that are never imaged before. However, there is a barrier for the propellent of generative AI in more business applications. That is, how users’ privacy in the chat prompt can be preserved. In this project, we propose to build a personal privacy-preserving prompt service for AI-powered large language models, such as ChatGPT. The proposed project will greatly broaden the current landscape of AI industry in Hong Kong. The launching of our MyGPTShield system and platform will not only benefit the end users (i.e., consumers), but also enrich business opportunities for AI driven developers and SMEs who rely on GPT services for their products and services. The project will start in November 2024 and last for 24 months. For inquiries, please contact Prof. Haibo Hu (haibo.hu@polyu.edu.hk). 

RCPST Origanized First Meeting with HUAWEI Technologies

The 2024 First Meeting with HUAWEI Technologies, hosted by The Research Centre for Privacy and Security Technologies in Future Smart Systems (RCPST) and The Hong Kong Polytechnic University (PolyU), concluded successfully on 27 September 2024. This landmark event united prominent industry leaders, distinguished academics, and the next generation of talent to share insights and partake in substantial dialogues. It served as a crucial forum for connecting scholarly progress with industrial innovation, enabling the exploration of cutting-edge advancements in AI Privacy and Security technologies.   PolyU’s Associate Vice President for Research and Innovation, Prof. WANG Zuankai, and the Head of the Department of Electrical and Electronic Engineering, Prof. CHUNG Chi-yung, warmly welcomed the collaborators from HUAWEI Technologies. They delivered inspiring opening remarks, emphasizing the importance of collaboration between academia and industry in driving technological advancements and addressing global challenges in privacy and security. The Director of RCPST, Associate Head and Professor of Electrical and Electronic Engineering, Prof. HU Haibo, also provided an insightful introduction to the research center. He highlighted the center's areas of expertise, mission, and core technologies, setting the stage for the day's discussions.   This introduction was followed by four thought-provoking keynote speeches delivered by leading experts: Prof. HU Haibo, Professor of COMP Prof. XIAO Bin, Professor of COMP Prof. LUO Xiapu, and Professor of COMP Prof. AU Man Ho Allen (represented by the Research Assistant Professor of COMP, Dr. LU Xingye). These distinguished speakers shared their recent advances in AI Privacy and Security, along with their successful collaborations with HUAWEI Technologies, offering a compelling glimpse into the future of these critical fields.   Then the event transitioned into a session dedicated to personal research introductions by eight promising junior researchers. Each researcher presented their innovative projects, focusing on various aspects of AI privacy and security. These presentations highlighted cutting-edge approaches to safeguarding data and ensuring privacy in increasingly complex digital environments. The junior researchers showcased a range of topics, from developing advanced encryption techniques to designing robust algorithms that can detect and mitigate security threats in real-time. Their work underscored the importance of interdisciplinary collaboration and the need for continuous innovation to address the evolving challenges in AI privacy and security.   The session provided a platform for these emerging scholars to engage with industry leaders and academic experts, fostering an environment of mentorship and collaboration. The exchange of ideas not only enriched the researchers' perspectives but also offered valuable insights into the practical applications of their work in real-world scenarios.   Concluding the event, representatives from HUAWEI Technologies shared several essential challenges currently faced by the industry. These challenges included the need for scalable privacy solutions that can keep pace with rapid technological advancements, the integration of AI systems into existing security frameworks, and the development of ethical guidelines for AI deployment. By highlighting these issues, HUAWEI underscored the critical role that academic-industry partnerships play in driving innovation and developing effective solutions.   Overall, the meeting served as a catalyst for future collaborations, inspiring both seasoned experts and emerging researchers to continue pushing the boundaries of AI privacy and security. The discussions and insights gained from this event are expected to pave the way for groundbreaking advancements in the field, ultimately contributing to a safer and more secure digital future.