Haoyu Han
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Haoyu Han has a total of 56 co-authors. Here are the top co-authors by number of shared publications:
- Jiliang Tang
Michigan State University, East Lansing, MI, USA
8 shared publications - Hui Liu
Michigan State University, East Lansing, MI, USA
4 shared publications - Yu Wang
University of Oregon
4 shared publications - Harry Shomer
University of Texas at Arlington, Arlington, TX, USA
3 shared publications - Yu Zhang
Texas A&M University, College Station, TX, USA
3 shared publications - Zhisheng Qi
University of Oregon, Eugene, OR, USA
3 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8268-8275
ConnectionMind: Leveraging Social Networks and Large Language Models for Personalized Recommendation at Meta
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8268-8275
Open AccessConnectionMind: Leveraging Social Networks and Large Language Models for Personalized Recommendation at Meta
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9718-9729
Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation (RAG)
Retrieval-Augmented Generation (RAG) has become a cornerstone of knowledge-intensive applications, including enterprise chatbots, healthcare assistants, and agentic memory systems. However, recent studies show that knowledge-extraction attacks can recover sensitive knowledge-base content through maliciously crafted queries, raising serious privacy and intellectual-property concerns. While prior work has explored individual attack and defense techniques, the research landscape remains fragmented across retrievers, generators, and evaluations based on non-standardized metrics and datasets. To address this gap, we introduce the first systematic benchmark for knowledge-extraction attacks on RAG systems. Our benchmark covers broad attack/defense strategies, representative retrieval embedding models, open/closed-source generators, (non) graph-based indexing, all evaluated under a unified framework with standardized protocols across multiple datasets spanning diverse languages. By consolidating the experimental landscape and enabling reproducible, comparable evaluation, this benchmark provides actionable insights and a practical foundation for developing privacy-preserving RAG systems in the face of emerging knowledge extraction threats.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9718-9729
Open AccessBenchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation (RAG)
Retrieval-Augmented Generation (RAG) has become a cornerstone of knowledge-intensive applications, including enterprise chatbots, healthcare assistants, and agentic memory systems. However, recent studies show that knowledge-extraction attacks can recover sensitive knowledge-base content through maliciously crafted queries, raising serious privacy and intellectual-property concerns. While prior work has explored individual attack and defense techniques, the research landscape remains fragmented across retrievers, generators, and evaluations based on non-standardized metrics and datasets. To address this gap, we introduce the first systematic benchmark for knowledge-extraction attacks on RAG systems. Our benchmark covers broad attack/defense strategies, representative retrieval embedding models, open/closed-source generators, (non) graph-based indexing, all evaluated under a unified framework with standardized protocols across multiple datasets spanning diverse languages. By consolidating the experimental landscape and enabling reproducible, comparable evaluation, this benchmark provides actionable insights and a practical foundation for developing privacy-preserving RAG systems in the face of emerging knowledge extraction threats.
- Top Cited PapersOpen Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 8966-8977
RAG vs. GraphRAG: A Systematic Evaluation and Key Insights
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 8966-8977
Top Cited PapersOpen AccessRAG vs. GraphRAG: A Systematic Evaluation and Key Insights
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1415-1426
Why Retrieval-Augmented Generation Fails: A Graph Perspective
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1415-1426
Open AccessWhy Retrieval-Augmented Generation Fails: A Graph Perspective
- Open Access
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1367-1370
Rigorizing Retrieval-augmented Generation with Structured Knowledge Intelligence (6 Hrs)
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1367-1370
Open AccessRigorizing Retrieval-augmented Generation with Structured Knowledge Intelligence (6 Hrs)
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6278-6279
The 2nd Workshop on Large Language Models for E-Commerce
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6278-6279
Open AccessThe 2nd Workshop on Large Language Models for E-Commerce
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6296-6297
Machine Learning on Graphs in the Era of Generative Artificial Intelligence
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6296-6297
Open AccessMachine Learning on Graphs in the Era of Generative Artificial Intelligence
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1308-1317
Unveiling Mode Connectivity in Graph Neural Network
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1308-1317
Open AccessUnveiling Mode Connectivity in Graph Neural Network
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 2699-2700
Large Language Model for E-Commerce Workshop
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 2699-2700
Open AccessLarge Language Model for E-Commerce Workshop
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 2837-2847
Spectral-Aware Augmentation for Enhanced Graph Representation Learning
Graph Contrastive Learning (GCL) has demonstrated remarkable effectiveness in learning representations on graphs in recent years. To generate ideal augmentation views, the augmentation generation methods should preserve essential information while discarding less relevant details for downstream tasks. However, current augmentation methods usually involve random topology corruption in the spatial domain, which fails to adequately address information spread across different frequencies in the spectral domain. Our preliminary study highlights this issue, demonstrating that spatial random perturbations impact all frequency bands almost uniformly. Given that task-relevant information typically resides in specific spectral regions that vary across graphs, this one-size-fits-all approach can pose challenges. We argue that indiscriminate spatial random perturbation might unintentionally weaken task-relevant information, reducing its effectiveness. To tackle this challenge, we propose applying perturbations selectively, focusing on information specific to different frequencies across diverse graphs. In this paper, we present GASSER, a model that applies tailored perturbations to specific frequencies of graph structures in the spectral domain, guided by spectral hints. Through extensive experimentation and theoretical analysis, we demonstrate that the augmentation views generated by GASSER are adaptive, controllable, and intuitively aligned with the homophily ratios and spectrum of graph structures.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 2837-2847
Open AccessSpectral-Aware Augmentation for Enhanced Graph Representation Learning
Graph Contrastive Learning (GCL) has demonstrated remarkable effectiveness in learning representations on graphs in recent years. To generate ideal augmentation views, the augmentation generation methods should preserve essential information while discarding less relevant details for downstream tasks. However, current augmentation methods usually involve random topology corruption in the spatial domain, which fails to adequately address information spread across different frequencies in the spectral domain. Our preliminary study highlights this issue, demonstrating that spatial random perturbations impact all frequency bands almost uniformly. Given that task-relevant information typically resides in specific spectral regions that vary across graphs, this one-size-fits-all approach can pose challenges. We argue that indiscriminate spatial random perturbation might unintentionally weaken task-relevant information, reducing its effectiveness. To tackle this challenge, we propose applying perturbations selectively, focusing on information specific to different frequencies across diverse graphs. In this paper, we present GASSER, a model that applies tailored perturbations to specific frequencies of graph structures in the spectral domain, guided by spectral hints. Through extensive experimentation and theoretical analysis, we demonstrate that the augmentation views generated by GASSER are adaptive, controllable, and intuitively aligned with the homophily ratios and spectrum of graph structures.