Prof Lam Kok Yan
Executive Director of the Digital Trust Centre, Singapore

Bio:

Prof Lam Kwok-Yan is Associate Vice President (Strategy and Partnerships) and Professor at Nanyang Technological University (NTU), Singapore, and Executive Director of the Digital Trust Centre (DTC), Singapore’s AI Safety Institute.

He has held leadership roles across NTU research centres and was on secondment to INTERPOL (Cyber and New Technology Innovation). He also serves on the International Telecommunication Union (ITU) Academic Advisory Body on Emerging Technologies.

His research spans cybersecurity, distributed systems, IoT security, blockchain, and quantum computing. He is also a serial entrepreneur, founding multiple tech start-ups in AI and security.

Prof Lam received his Ph.D. from University of Cambridge and was inducted into the Singapore Cybersecurity Hall of Fame in 2022.

Talk Title: Building Digital Trust: Decentralized Identity and AI Safety in the Digital Era

Talk Abstract: Digital Trust is fundamental to the adoption and growth of the digital economy. To build trust in the digital space, one key requirement is the enforcement of accountability, which must be established not only for users and business entities, but also for AI agents in the emerging trend of increasing adoption of AI-empowered autonomous processing. In this connection, Trusted Digital Identity serves as the foundation and infrastructure, enabling trusted interactions and transactions across stakeholders in the digital ecosystem. At the same time, ensuring safe and responsible behaviors of AI models has become another critical issue as AI agents increasingly perform transactions and decision-making without human intervention. In this talk, we first introduce our work on decentralized identity systems as a new paradigm for secure, privacy-preserving, and resilient trust infrastructure across organizational and national boundaries. Unlike traditional centralized identity systems, which suffer from risks such as large-scale data breaches, excessive concentration of sensitive information, and the unrealistic assumption of a single authority in a borderless, heterogeneous world, decentralized identity systems allow stronger privacy, security, and control over digital identities without the presence of a single authority. We then discuss the importance of AI Safety in establishing digital trust. AI model risks erode trust and hinder adoption by producing unreliable or biased outputs, and they increase the likelihood of privacy breaches and data manipulation. Neglecting risk management can lead to operational disruption, penalties, liability, and reputational damage. Accordingly, we have conducted multilingual agentic testing to evaluate the safety of agentic AI systems across diverse languages and cultural contexts. The testing framework simulates real-world tasks in which autonomous agents coordinate across tools and interact with users, emphasizing boundary enforcement, traceability, reversibility, and a responsive human-in-the-loop.

https://personal.ntu.edu.sg/kwokyan.lam/ 

Prof Elisa Bertino

Bio:  Elisa Bertino is a Samuel D. Conte Distinguished Professor of Computer Science at Purdue University. She has worked for more than 40 years in data security and privacy. Her research interests include machine learning techniques for cybersecurity, security of cellular networks,  zero-trust architectures, and agentic AI security. In the area of machine learning for cybersecurity, she led the design of transfer learning techniques for network attack detections and for detection and classification of malware. In the area of cellular network security, she led the design of the LTEInspector and 5Greasoner frameworks to test security properties of cellular networks leading to the identification of ten novel vulnerabilities in the 4G LTE (Long Term Evolution) and 5G standards, and the discovery of new privacy attacks in 4G and 5G cellular protocols. For this work, she was named to the GSMA (Global System for Mobile Communications Association) Mobile Security Research Hall of Fame. More recently she has been working on machine learning techniques for detecting malicious base stations and attacks to synchronization protocols for O-RAN. She is a Fellow member of IEEE, ACM, and AAAS. She received the 2002 IEEE Computer Society Technical Achievement Award, the 2005 IEEE Computer Society Tsutomu Kanai Award, the 2019-2020 ACM Athena Lecturer Award, and the 2021 IEEE Innovation in Societal Infrastructure Award. She is currently serving as ACM Vice President.

Talk Title: AI Agentic Security: Safeguarding the Next Generation of Autonomous Systems

Talk Abstract: 

https://www.cs.purdue.edu/people/faculty/bertino.html  

Prof Marten van Dijk 

Bio: Marten van Dijk is group leader and founder of the Computer Security group at CWI, the Netherlands, with over 20 years of experience in both industry (Philips Research and RSA Laboratories) and academia (MIT, University of Connecticut, Vrije Universiteit van Amsterdam). His work has been recognized by the IEEE CS Edward J. McCluskey Technical Achievement Award 2023, the A. Richard Newton Technical Impact Award in Electronic Design Automation 2015, and has received several best and test-of-time paper awards. He is an IEEE Fellow.

Talk Title: "AI: Its Security and Trustworthiness"

Talk Abstract: AI in the form of Large Language Models (LLM) has been shaping our digital living space. It has shown great technical progress and applications. On the other hand its security and trustworthiness is in mild terms "brittle." It can be used by attackers to improve their capability of finding and exploiting attack points, the LLM itself can be a threat, privacy of training data is in question, etc. In this presentation we look at various recent developments and show that we have learned a lot, but that the path toward making LLMs safe to use and be trustworthy is still a long one ahead of us.

https://www.cwi.nl/en/people/marten-van-dijk/ 

Prof Yang Xiang

Bio: Professor Yang Xiang received his PhD in Computer Science from Deakin University, Australia. He is currently a full professor and the Director of Digital Capability Research Platform, Swinburne University of Technology, Australia. In the past 20 years, he has been working in the broad area of Cybersecurity, which covers software, system, network, and application security. He has published more than 300 research papers in many international conferences and journals in Cybersecurity, such as ACM CCS, IEEE S&P, Usenix Security, NDSS, IEEE TDSC, and IEEE TIFS. He is the Editor-in-Chief of the SpringerBriefs on Cyber Security Systems and Networks. He serves as the Associate Editor of the ACM Computing Surveys. He served as the Associate Editor of IEEE Transactions on Dependable and Secure Computing, IEEE Internet of Things Journal, IEEE Transactions on Computers, and IEEE Transactions on Parallel and Distributed Systems. He is a current member of College of Experts (CoE) of the Australian Research Council (ARC). He is a Fellow of the IEEE.

Talk Title: From Agentic AI to Software, Models, and the Physical World

Talk Abstract: The rapid evolution of AI has shifted systems from passive models to agentic AI capable of autonomous reasoning, code generation, and interaction with real-world environments. While these advances enable powerful applications, they fundamentally challenge existing assumptions in security, software engineering, and governance. This talk synthesises recent research that reframes AI security as a cross-layer lifecycle problem, spanning learning models, LLM-enabled software, autonomous agents, and cyber-physical systems. We examine how agentic LLMs expand the attack surface, enabling dynamic extraction, evasion of vulnerability detection, and systematic ethical and compliance failures in code generation. At the model level, persistent backdoors and adversarial perception further undermine trust. As AI systems increasingly operate in IoT and safety-critical environments, this talk argues for trustworthiness by design, integrating agent-aware threat models, continuous auditing, and robust learning foundations across the AI lifecycle, and inspire the next generation of research in trustworthy and resilient AI.

Prof Surya Nepal

Bio: Dr Surya Nepal is a senior principal research scientist at CSIRO’s Data61. He has been with CSIRO since 2000 and currently serves as acting Deputy Director/Science Director of Data61. His primary research focuses on developing and implementing technologies for distributed systems, with a specific emphasis on security, privacy, and trust. Dr Nepal has over 300 peer-reviewed publications to his credit. Additionally, Dr Nepal is an adjunct professor at UNSW and an honorary professor at Macquarie University. He is a Fellow of IEEE.

Talk Title: CiNTEL4Cyber: Human–AI Dynamics in Engineering Trustworthy AI Systems

Talk Abstract: Security Operations Centres (SOCs) are critical to defending organisations against evolving cyber threats, serving as central hubs for detecting, analysing, and responding to security incidents. However, the growing volume of alerts has led to alert fatigue, increasing the risk that critical threats are missed. In response, there is growing interest in leveraging AI to either automate analysts’ tasks or augment their capabilities, thereby improving productivity. At the core of this choice lies a fundamental challenge: trust in the AI system. In this presentation, we argue for moving beyond a narrow focus on automation or augmentation. Instead, we advocate for collaborative intelligence (CINTEL)—the design of practical AI systems for SOCs in which humans and AI work together, leveraging their complementary strengths and mitigating each other’s limitations. Recent advances in AI and its growing integration into SOC workflows make a compelling case for adopting CINTEL as a pathway to building trustworthy AI systems for SOCs. We present our vision and research outcomes from the CINTEL for Cybersecurity project.

Prof Cong Wang

Bio: Cong Wang is a Chair Professor and the Head of Computer Science Department at City University of Hong Kong. His research spans data security and privacy, AI systems and security, and blockchain and decentralized application security. He is an IEEE Fellow, a Founding Member of the Hong Kong Young Academy of Sciences, and a co-recipient of the 2024 BOCHK Science and Technology Innovation Prize. He has served as the Editor-in-Chief of IEEE Transactions on Dependable and Secure Computing.

Talk Title: AI x Cybersecurity: Navigating Challenges and Embracing Opportunities

Talk Abstract: As AI becomes deeply embedded across the digital stack, the intersection of AI and security has become a critical frontier. This talk examines this evolving landscape, dissecting the expansion of attack surfaces within AI infrastructure, the weaponization of AI for sophisticated exploitation, and the strategic roadmaps required to secure our future. We conclude with a deep dive into recent advancements from CityUHK CS focused on the synergy of AI, security, and trustworthy systems.

A/Prof Xiaoxiao Li

Bio:  Dr. Xiaoxiao Li is an Associate Professor in the Department of Electrical and Computer Engineering at the University of British Columbia, a Faculty Member at the Vector Institute, and Visiting Faculty Member at Google. Dr. Li holds a Canada Research Chair (Tier II) in Responsible AI and is recognized as a Canada CIFAR AI Chair. Dr. Li's research aims to enhance the trustworthiness and efficiency of AI models, bridging the gap between cutting-edge AI research and practical real-world applications, such as healthcare. Dr. Li’s current interests include mechanistic analysis of large language and vision-language models (LLMs/VLMs), developing hypothesis-driven evaluations, and advancing methodologies toward artificial general intelligence (AGI). 

Title Title: Diagnosing, Routing, and Recovering from Errors in LLM Agent Optimization and Deployment

Talk Abstract:

Dr Thuan Pham

https://thuanpv.github.io/ 

Prof Hyoungshick Kim

Bio: Hyoungshick Kim is a Full Professor in the Department of Software at Sungkyunkwan University. He received his PhD from the Computer Laboratory at the University of Cambridge (2008–2011).

Prior to his current role, he worked as a Senior Engineer at Samsung Electronics (2004–2008), a Postdoctoral Fellow at the University of British Columbia (2012–2013), and a Distinguished Visiting Scientist at CSIRO Data61 (2019–2020).

An active researcher in cybersecurity, Professor Kim has published around 250 papers with over 7,900 citations, including 32 papers at top-tier conferences such as IEEE S&P, ACM CCS, and USENIX Security. He frequently serves on programme committees for leading conferences, including CCS, USENIX Security, ACSAC, and ASIACCS, and is Associate Editor-in-Chief of IEEE Transactions on Services Computing.

In addition, he serves as a Court Expert Commissioner and as an advisor to Samsung Electronics and LG Electronics.

https://seclab.skku.edu/people/hyoungshick-kim/ 

Prof Carsten Maple

Ms Seah Park 

Bio: Seah Park is a Visiting Scholar at the Nanyang Technological University (NTU) Digital Trust Centre and serves as a Director at the Ministry of Foreign Affairs of the Republic of Korea

Talk Title: AISI Work In Korea

Dr Huayi Duan

Dr Feng Liu

A/Prof Noriziana Jamil

Dr Yuefeng Du

Bio: Dr. Yuefeng Du is a Researcher and Lecturer in the Department of Computer Science at City University of Hong Kong. He received his PhD in Computer Science from CityU in 2022. His research lies in applied cryptography, blockchain, and network security, with a particular focus on decentralised storage systems, zero-knowledge auditing, and blockchain-enabled validation.

Dr. Du’s work addresses practical security and privacy challenges in emerging decentralised infrastructures, including secure data auditing, privacy-preserving verification, and trustless blocklisting. By combining rigorous cryptographic design with system-oriented evaluation, his research aims to bridge the gap between theory and practice and to develop scalable, trustworthy mechanisms for real-world digital ecosystems.

https://scholars.cityu.edu.hk/en/persons/yuefengdu2/