Scholar
Yanbo Dai
Google Scholar ID: t4oYytgAAAAJ
The Hong Kong University of Science and Technology
Citations & Impact
Citations
73
H-index
3
i10-index
3
Publications
8
Co-authors
5
list available
Contact
Publications
Resume (English only)
Academic Achievements
- - Selected Publications:
- - Disabling Self-Correction in Retrieval-Augmented Generation via Stealthy Retriever Poisoning
- - EAMET: Robust Massive Model Editing via Embedding Alignment Optimization
- - TrojanDam: Detection-Free Backdoor Defense in Federated Learning through Proactive Model Robustification utilizing OOD Data
- - BackdoorIndicator: Leveraging OOD Data for Proactive Backdoor Detection in Federated Learning
- - Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning
- - Deep Domain Adaptation for Predicting Intra-Abdominal Pressure with Multichannel Attention Fusion Radar Chip
- - Academic Services: Reviewer: ICLR’25-26; Sub-Reviewer: ICML’25, Neurips’25, AAAI’25, CCS’25, IEEE S&P’24-25
- - Teaching: Teaching Assistant, COMP1944 - Artificial Intelligence Ethics, HKUST, 2024 Fall; Teaching Assistant Coordinator, HKUST, 2025 Fall, 2026 Fall
Research Experience
- - Research Assistant, School of Cyber Science and Engineering, Southeast University, hosted by Prof. Songze Li, Jun. 2024 - Aug. 2024
- - Summer Research Internship, Department of EEE, The University of Hong Kong, hosted by Prof. Y.C. Wu, Jun. 2021 - Aug. 2021
Education
- - Ph.D. in Computer Science and Engineering, HKUST, Aug. 2024 - Present, Advisor: Prof. Shuai Wang
- - M.Phil. in Internet of Things, HKUST(GZ), Sep. 2022 - Jun. 2024, Advisor: Prof. Songze Li
- - B.Eng. in Electronic Information Engineering, Chongqing University, Sep. 2018 - Jun. 2022, Advisor: Prof. Hailin Cao
Background
- - Research Interests: AI Security, with a recent focus on LLMs; Model Editing and its security applications; Backdoors Attacks & Defenses in Federated Learning
- - Professional Field: Computer Science and Engineering
- - Brief Introduction: A second-year Ph.D. student at the CSE department of HKUST, committed to enhancing the security and reliability of large language models (LLMs).
Miscellany
- - Personal interests, hobbies, etc., not provided
