About Me

I am currently a Research Fellow at Nanyang Technological University (NTU), working with Prof. Wei Yang Bryan Lim and Prof. Cyril Leung in Midori Lab. Before this, I received my Ph.D. degree in 2025 from the School of Cyberspace Science and Technology at Beijing Jiaotong University, supervised by Prof. Jiqiang Liu and Prof. Wei Wang. From 2024 to 2025, I was a visiting student at Nanyang Technological University.


My research mainly focuses on Trustworthy AI, with a particular focus on poisoning attacks and defence mechanisms in distributed deep learning systems. Recently, my research has shifted toward trustworthiness in Multimodal LLM and agent, where I explore potential vulnerabilities and develop robust defence mechanisms to enhance their integrity and user trust.

News

  • May 2026🎉 Four papers are accepted by ICML 2026!
  • Mar 2026🎉 Our work is accepted by WWW 2026!
  • Dec 2025🎉 Our work is accepted by NeurIPS 2025!
  • Oct 2024🎉 Our work is accepted by IEEE TIFS!
  • Jul 2024🎉 Our work is accepted by ACM CCS 2024!

Selected Publications [Google Scholar] [DBLP]

* Equal contribution, † Corresponding author (for publications)
VenomRec thumbnail

VenomRec: Cross-Modal Interactive Poisoning for Targeted Promotion in Multimodal LLM Recommender Systems

Guowei Guan, Yurong Hao†, Jiaming Zhang, Tiantong Wu, Fuyao Zhang, Tianxiang Chen, Longtao Huang, Cyril Leung, Wei Yang Bryan Lim.

ICML 2026
Paper Code
# Trustworthy AI # Multimodal LLM # Recommender Systems
ModelPirate thumbnail

An Empirical Study on the Resilience of Partial Merging to Model Clone Attacks

Tiantong Wu, Yurong Hao†, Wei Yang Bryan Lim.

ICML 2026
Paper
# Model Merging # Model Security
SubspacePath thumbnail

SubspacePath Pruner: Inference-time Pruning via Probe-based Representation–Parameter Coupling

Zhiren Gong, Yikun Hou, Fan Wu, Che Wang, Fuyao Zhang, Tiantong Wu, Yurong Hao, Jiaming Zhang, Yiyang Duan, Tiantong Wang, Fei Huang, Chau Yuen, Wei Yang Bryan Lim.

ICML 2026
Paper Project
# Model Efficiency # Inference-Time Pruning # Routing
XDomainBench thumbnail

XDomainBench: Diagnosing Reasoning Collapse in High-Dimensional Scientific Knowledge Composition

Zhiren Gong, Tiantong Wu, Jiaming Zhang, Fuyao Zhang, Che Wang, Yurong Hao, Yikun Hou, Foo Ping, Yilei Zhao, Fei Huang, Chau Yuen, Wei Yang Bryan Lim.

ICML 2026
Paper Code Project
# LLM Evaluation # Scientific Reasoning # Benchmark and Datasets
Spattack thumbnail

Spattack: Subgroup Poisoning Attacks on Federated Recommender Systems

Bo Yan, Yurong Hao, Dingqi Liu, Huabin Sun, Pengpeng Qiao, Wei Yang Bryan Lim, Yang Cao, Chuan Shi.

WWW 2026 Oral
Paper
# Federated Learning # Poisoning Attacks
AegisGuard thumbnail

AegisGuard: RL-Guided Adapter Tuning for TEE-Based Efficient & Secure On-Device Inference

Che Wang, Ziqi Zhang, Yinggui Wang, Tiantong Wang, Yurong Hao, Jianbo Gao, Tao Wei, Yang Cao, Zhong Chen, Wei Yang Bryan Lim.

NeurIPS 2025
Paper
# On-Device Inference # TEE Security # Reinforcement Learning
StairClimbing thumbnail

Eyes on Federated Recommendation: Targeted Poisoning With Competition and Its Mitigation

Yurong Hao, Xihui Chen, Wei Wang, Jiqiang Liu, Tao Li, Junyong Wang, Witold Pedrycz.

IEEE TIFS
Paper
# Federated Recommendation # Targeted Poisoning Attack # Targeted Defence
FRecAttack2 thumbnail

Not One Less: Exploring Interplay between User Profiles and Items in Untargeted Attacks against Federated Recommendation

Yurong Hao, Xihui Chen, Xiaoting Lyu, Jiqiang Liu, Yongsheng Zhu, Zhiguo Wan, Sjouke Mauw, Wei Wang.

ACM CCS 2024 Oral
Paper
# Untargeted Poisoning Attacks # Untargeted Defence

Patents

  • Method for Privacy Leak detection method For Vertical Federated Learning Based on Feature Embedding Analysis, Wei Wang, Yurong Hao, et al., CN116341004B, in Chinese. China Patent Granted
  • Defence Method for Federated Learning Poisoning Attacks, Wei Wang, Yurong Hao, et al., CN116527393A, in Chinese. China Patent Granted
  • Local Differential Privacy Method for Government Data Sharing. Chunhui Piao, Yurong Hao, et al., CN112329056B, in Chinese. China Patent Granted
  • Privacy-Preserving Method for POI Recommendation. Wei Wang, Yurong Hao, et al., CN117272370B, in Chinese. China Patent Granted

Monographs

  • Wei Wang et al., Privacy Preserving Computation[M], People's Posts and Telecommunications Press, 2023. Contributed to the writing of Section 8 (Differential Privacy)
  • Wei Wang et al., Artificial Intelligence Security Assessment Technology[M], Hans Publishing House, 2023. Served as an Editorial Board Member

Research Projects

  • Privacy Preserving Recommender System, Ant Group. PI
  • Privacy Preserved Methods for Federated Recommendation, Central Universities Basic Scientific Research Business Fund Project. PI
  • Privacy Preserved Methods for Government Data Sharing, innovation project for M.S. students. PI
  • Artificial Intelligence System Security Testing and Robust Enhancement Software and Hardware Integration, National Major Project. Participated in Project Application, Management and Tech Research
  • Research on key technologies for security detection and protection of artificial intelligence applications, National Major Project. Participated in Technology Research and Development
  • Trustworthy Mechanism and Key Technologies of Urban Intelligent Systems, National Key R&D Program Project. Participated in Technology Research and Development

Invited Talks

  • Nov 2025Security and Privacy in Personalised AI: From Federated to Multimodal LLM-based Recommender Systems, Institute of Science Tokyo, Tokyo, Japan.
  • Oct 2024Not One Less: Exploring Interplay between User Profiles and Items in Untargeted Attacks against Federated Recommendation, ACM CCS 2024 Oral, Salt Lake City, The United States.
  • Sep 2024Trustworthy AI-poisoning Attacks & Defence, Nanyang Technological University, Singapore.