About N-CRiPT
Introduction to N-CRiPT
NUS Centre for Research in Privacy Technologies (N-CRiPT) is a strategic capability research centre in privacy-preserving technologies established by National University of Singapore. The Centre is funded by National Research Foundation, and administered by Smart Systems Research Programme Office, Info-communications Media Development Authority. Working ‘Towards a privacy-aware Smart Nation’, our goal is to develop privacy-preserving technologies to protect privacy at an individual and organizational level in a holistic manner – with focus on, but not limited to, unstructured data – along the whole data life cycle.
Research areas
- Privacy-aware Data Sensing and Gathering Platform
- Privacy-preserving Models and Data Publishing
- Collaborative Private Computation
- Privacy Risk Management
Technical Program
Registration
Venue: Level 1@Della & Seng Gee Guild Hall, NUSS Kent Ridge Guild House, NUS
Opening Remarks
Prof. Mohan Kankanhalli (Director, N-CRiPT)
Invited Talk 1
Trustworthy Media
Prof. Nasir Memon (New York University)
Technical Session 1 (Privacy-Preserving Models & Data Publishing)
Synthesizing Relational Data with Differential Privacy
Prof. Xiao Xiaokui (National University of Singapore)
Bias Propagation in Federated Learning
Chang Hongyan (National University of Singapore)
Differentially Private Federated Bayesian Optimization with Distributed Exploration
Dr. Dai Zhongxiang (National University of Singapore)
Poster Session & Tea Break
Technical Session 2 (Collaborative Private Computation)
Finding Stable Clusters over Generic, Heterogeneous Data: Method and Applications
Prof. Anthony Tung (National University of Singapore)
Curious or Malicious: Towards Different Security Levels in Privacy-preserving Computation
Dr. Song Xiangfu (National University of Singapore)
Towards Trustworthy Human-Centered Explainable AI
Prof. Brian Lim (National University of Singapore)
Lunch Break
The Future & Challenges of Digital Trust
Introduction to the National Digital Trust Centre
Prof. Lam Kwok Yan (Nanyang Technological University)
Panel Discussion
Moderator
Prof. Mohan Kankanhalli (Director, N-CRiPT)
Panel
Prof. Lam Kwok Yan (Nanyang Technological University)
Prof. Robert Deng (Singapore Management University)
Prof. Geng Weidong (Zhejiang University)
Poster Session & Tea Break
Technical Session 3 (Privacy-Aware Data Sensing & Gathering Platform)
Vision-and-Language Research: Towards Universal Multimodal Intelligence
Dr. Li Junnan (Salesforce Research Asia)
Combining Common Knowledge with Deep Learning Models
Xu Ziwei (National University of Singapore)
Collaborative Split Learning Framework for Smart Grid Load Forecasting
Dr. Asif Iqbal (National University of Singapore)
Invited Talk 2
Towards Trustworthy Perception for Intelligent Machines
Prof. Yang Yi (Zhejiang University)
Closing Remarks
Prof. Anthony Tung (Deputy Director, N-CRiPT)
Workshop Dinner
Venue: Peppermint, Level 4 PARKROYAL COLLECTION Marina Bay, Singapore 039594
Keynote Speakers
Prof. Nasir Memon
Vice Dean for Academic and Student Affairs,
Professor of Computer Science and Engineering,
Tandon School of Engineering,
New York University
Trustworthy Media
Abstract: Rapid progress in machine learning, computer vision and graphics has led to democratization of media manipulation capabilities. While convincing photo and video manipulation used to require substantial time and skill, modern editors bring (semi-) automated tools that can be used by everyone. At the same time, dissemination of fake news and misinformation campaigns are picking up speed and eroding trust within society. Our media distribution platforms lack content integrity features as they were designed and optimized for the quality of (human) experience. This talk will discuss approaches that are being developed to return integrity and trust in digital media.
Bio: Nasir Memon is a professor in the Department of Computer Science and Engineering at NYU Tandon. He is an affiliate faculty at the computer science department in the Courant Institute of Mathematical Sciences at NYU. He introduced cyber security studies to New York University Tandon School of Engineering and is a founding director of the Center for Cyber Security, New York University, and the Center for Cyber Security at New York University Abu Dhabi. He is the founder of OSIRIS and CSAW, the worlds largest student run cyber security event. As the Associate Dean for Online Learning, he launched the Bridge to Tandon program that provides pathways to Non-STEM students to Computer Science and Cyber Security Cyber Fellows program that provides a highly affordable, industry partnered online MS in cyber security to domestic students and the MS in Cyber Risk and Strategy in collaboration with NYU Law. He has published more than 300 papers and received several best paper awards and awards for excellence in teaching. He has been on the editorial boards of several journals, and was the Editor-In-Chief of the IEEE Transactions on Information Security and Forensics. He is an IEEE, IAPR and SPIE Fellow for his contributions to image compression and media security and forensics. His research interests include digital forensics, biometrics, data compression, network security and security and human behavior.
Prof. Yang Yi
Professor, Zhejiang University
Towards Trustworthy Perception for Intelligent Machines
Abstract: In today's technology-driven world, human society is keenly seeking for game-changing intelligent machines that can be trusted. Perception, as a fundamental element of such systems, plays an integral role in their optimal functioning. As such, the assurance of trustworthy perception assumes paramount significance in upholding the trustworthiness of the entire intelligent system. In this talk, I will expound upon four dimensions crucial to trustworthy perception, namely Robustness, Explainability, Safety, and Privacy; and showcase our four recent studies that concentrate on each of these dimensions. The discussion will commence by delving deeply into the issue of open-world perception in autonomous driving, which is a critical challenge necessitating robust perception. I will then share our latest advance towards language-capable, interaction-centric embodied AI, which earns human trust through bi-directional human-robot communication. After that, I will elucidate the use of federated learning to safeguard sensitive image data during deep model training, and further examine the vulnerability of deep video models to adversarial attacks, a great threat to the safety and security of autonomous systems. This talk will be concluded by examining the topic with an open and enquiring flavor, teasing apart open challenges in the fast-developing realm of trustworthy perception for intelligent machines.
Bio: Prof. Yang Yi is a Chair Professor at Zhejiang University. His research interests include machine learning and its applications to multimedia content analysis and computer vision. His work has been recognized by a number of prestigious awards, including the Digital Innovation Award from the Australian Computer Society, the Australian Research Council Lifetime Achievement Award, the AWS Machine Learning Awards, and the Top Lifetime Achiever Award by The Australian. He has been a Clarivate Analytics Highly Cited Researcher for the past five years. He has received more than 40 awards in international scientific research competitions, including 20+ best-performance winners. He has received over 51,000 Google Scholar citations and his H-index is 111.
Panel Discussion - The Future and Challenges of Digital Trust
Moderator
Prof. Mohan Kankanhalli
Provost's Chair Professor of Computer Science,National University of Singapore; Director, N-CRiPT; Deputy executive chairman, AI SingaporePanel Member
Prof. Lam Kwok Yan
Executive Director, National Centre for Research in Digital Trust (DTC); Professor, School of Computer Science & Engineering, Nanyang Technological UniversityPanel Member
