Biography: Prof. Jun Dai is an Associate Professor in the Department of Computer Science at Worcester Polytechnic Institute (WPI). He received his Ph.D. degree in Information Sciences and Technology from Pennsylvania State University, with a specialization in cybersecurity. He also holds a master’s degree in Network Science and Engineering and a bachelor’s degree in Information Security from University of Science and Technology of China. His research spans networks, distributed systems, artificial intelligence, and cybersecurity, with recent focus on large language model security, autonomous agent security, advanced attack detection, vulnerability analysis, secure coding, and cybersecurity education. Dr. Dai has published extensively in leading venues, including NDSS, ICML, ACM SenSys, ACM SIGMOD, IEEE TDSC, IEEE TIFS, and ACM SIGCSE. He currently serves as an Associate Editor for IEEE TDSC and regularly reviews for top-tier conferences such as ACM CCS and ICDCS, as well as premier journals including TIFS, TDSC, TVT, and TMC. He served as Workshop Chair for CCS 2023 and is currently co-chairing the Artifact Evaluation Committee for CCS 2026.
Speech Title: From Internal Representations to Trustworthy LLMs: Robustness, Privacy, and Provable Defense
Abstract: As Large Language Models (LLMs) become foundational to scientific discovery, data-driven decision making, and autonomous systems, ensuring their trustworthiness has emerged as a central challenge. The integration of external knowledge through Retrieval-Augmented Generation (RAG) and the widespread adoption of open-source LLMs significantly expand both capability and risk, introducing new attack surfaces and raising fundamental questions about robustness, privacy, and reliability. This talk advances a representation-centric perspective on LLM security, arguing that the key to trustworthy AI lies not only in what models produce, but in how they internally represent knowledge. By analyzing neural activations across layers, it becomes possible to detect adversarial manipulation, characterize the imprint of training data, and design systems that are resilient by construction. Building on this insight, the talk traces a progression from activation-based detection of poisoned responses, to understanding data memorization through internal representations, and ultimately to the development of provably robust retrieval mechanisms that bound adversarial influence. Together, these results point toward a new paradigm for securing AI systems, shifting from reactive, output-level safeguards to principled, representation-level reasoning, and outline a path toward trustworthy AI systems capable of operating reliably in adversarial, data-rich, and high-stakes environments.
Biography: Kaizhu Huang works on trustworthy machine learning, and neural/biomedical information processing. Before joining DKU, he was a full professor at Xi’an Jiaotong-Liverpool University (XJTLU) and Associate Dean of research in School of Advanced Technology, XJTLU. He was also Head of EEE, at XJTLU from 2016 to 2019. He worked at Fujitsu Research Centre, CUHK, University of Bristol, National Laboratory of Pattern Recognition, Chinese Academy of Sciences from 2004 to 2012. He was the recipient of the 2011 Asia Pacific Neural Network Society Young Researcher Award. He received the best paper or book awards for seven times. He has published 10 books and over 280 international research papers including 150+ journal papers (e.g. IEEE T-PAMI, IEEE T-IP, IEEE T-NNLS, IEEE T-CYB, JMLR) and 140+ conference papers (e.g. AAAI, IJCAI, SIGIR, NeurIPS, UAI, CIKM, ICDM, ICML, ECML, CVPR, ICCV). He is Editor in Chief, Elsevier CSSI and serves as associated editors/advisory board members in a number of international journals and book series. He was invited as a keynote speaker in more than 50 international conferences or workshops. He has led 5 NSFC major or general program projects, all as PI.
Title of Speech: Bridging Data Augmentation with Model Generalization: Methods, Theory, and Outlook
Abstract: Data augmentation and model generalization are fundamental topics in machine learning. This talk seeks to provide a systematic introduction that bridges these areas from both theoretical and practical perspectives. Specifically, it will examine the theoretical foundations and practical impact of data augmentation in enhancing model generalization and robustness. The discussion will encompass local and global data augmentation techniques, extensions of adversarial training, large language model (LLM)-based data augmentation, and physics-informed augmentation strategies. By establishing theoretical connections between these approaches and model generalization, the talk will present practical applications of data augmentation in domains such as medical analysis, industrial anomaly detection, and point tracking. The content is primarily based on the team’s recent research published in leading AI conferences, including AAAI 2023, NeurIPS 2024, CVPR 2025, Siggraph 2026, and ACL 2026.
Biography: Zhengchuan Chen (M’16) received the B.S. degree from Nankai University, China, in 2010 and the Ph.D. degree from Tsinghua University, China, in 2015. He visited The Chinese University of Hong Kong in 2012 and visited University of Florida, USA, in 2013. From 2015 to 2017, he was a Postdoctoral Fellow in the Information Systems Technology and Design Pillar, Singapore University of Technology and Design (SUTD). He is currently a Professor with the School of Microelectronics and Communication Engineering, Chongqing University, China. His main research interests include 5G and beyond wireless communications, age of information, and network information theory.
Dr. Chen serves as the editor of IEEE Open Journal of the Communications Society，the editor of Digital Communications and Networks. He has also served several IEEE conferences, e.g., the IEEE Globecom, as a Technical Program Committee Member. He was selected as an Exemplary Reviewer of the IEEE Transactions on Communications in 2015. He coreceived the Best Paper Award at the International Workshop on High Mobility Wireless Communications in 2013.
Title of Speech: How to improve the information freshness in status updating systems： A queueing theory perspective
Abstract: With the rapid development of new-generation communication technologies such as the Internet of Things (IoT) and 5G, delay-sensitive services are increasingly proliferating. Timely provision of status information about physical processes is crucial for decision-making control and state estimation in real-time applications like vehicular networks. The growing demand for real-time data transmission further exacerbates the inherent conflict between information timeliness and limited network resources, posing significant challenges to the design of wireless sensing networks. Given the pertinence of the Age of Information (AoI) in characterizing the freshness and timeliness of received information, it is usually adopted as the information timeliness performance metric. To address the information timeliness issue in multi-flow status update systems where multiple sources share a single server, a centralized resource scheduling strategy is proposed to enhance the system's AoI performance. For the data generation rate control problem in large-scale status update systems, a game theory-based decentralized node data generation rate control algorithm is proposed. To tackle the challenge where a single sensing node cannot meet real-time status update requirements, a parallel transmission strategy is introduced to improve the system's AoI performance. The obtained results provide insights for the design and resource allocation of communication systems targeting emerging real-time applications such as intelligent transportation.
Biography: Prof. Zhi Li is a distinguished member of China Computer Federation (CCF), former standing committee member of its Technical Council on Software Engineering (TCSE), and a member of its Technical Council on Systems Software, Service Computing and Formal Methods, senior member of IEEE and ACM. He graduated with a BSc degree from Fudan University in 1991, an MSc degree from the University of York in 2004, and a PhD degree from The Open University in 2008. Prof. Li had spent over 10 years doing professional and technical work before he entered academia in 2001, with subsequent 9 years in the UK. His research interests are modeling, verifying, testing and validating Human-Cyber-Physical Systems (HCPSs) based on a problem-oriented approach, Artificial Intelligence for Requirements Engineering (AI4RE), Artificial General Intelligence (AGI), and Human-Computer Interaction (HCI). His research has been sponsored by 3 grants from the National Natural Science Foundation of China, and 5 grants from Ministry of Education of China, Guangxi Natural Science Foundation, and Guangxi Scientific Research & Technological Development. He has published over 80 research papers at international journals and conferences (including TSE, TKDE, FSE2025, Journal of Software, 3 best conference papers). He has given 2 keynote speeches and over 20 invited talks in international conferences, and he is the leader and one of the main contributors to a suite of Computer-Aided Requirements Engineering (CARE) tools for Problem-Oriented Software Development (POSD).
Title of Speech: Explainability and Verifiability of AI Systems for Human-Cyber-Physical Systems (HCPS)
Abstract: The advancement of artificial intelligence has accelerated the deep integration of humans, cyber space and physical entities. As a typical software-intensive system, Human-Cyber-Physical Systems (HCPS) undertake the core task of coordinating and managing various participants. Its success relies not only on software and hardware design, but more importantly on whether the integration of humans, cyber components and physical devices can meet system requirements and satisfy practical user needs. The overall operational performance of HCPS hinges fundamentally on the collaboration and adaptation among the above three elements. Characterized by its openness, HCPS exhibits significant behavioral uncertainty, which poses challenges to the analysis and verification of key indicators such as system safety and reliability. Consequently, the explainability and verifiability of AI have become a major research focus in this field. This talk will conduct an in-depth discussion on the above issues. It points out that effective communication and interaction among diverse audiences and stakeholder is the key to the implementation of explainable AI. Furthermore, in this talk I will demonstrate that building upon causal reasoning theories combined with structured scenario modeling is a highly promising technical framework for constructing explainable artificial intelligence systems.
Copyright © 2026 the 9th International Conference on Big Data and Artificial Intelligence (BDAI 2026). All rights reserved.
