Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Minghui Xu

Minghui Xu

5 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

Crypto×5Distributed×1ML×1

Frequent co-authors

Xiuzhen Cheng5×
Yue Zhang2×
Tianyi Sun1×
Shuo Liu1×
Zhijun Li1×
Huayi Qi1×

Research Timeline

2026
Graph-Aware Stealthy Poison-Text Backdoors for Text-Attributed Graphs

The paper proposes TAGBD, a graph-aware backdoor attack that demonstrates that inconspicuous poison text alone can reliably compromise text-attributed graph learning systems.

SAGE: Signal-Amplified Guided Embeddings for LLM-based Vulnerability Detection

The paper proposes SAGE, a framework that uses Signal-Amplified Guided Embeddings to overcome 'Signal Submersion' in LLMs, significantly boosting vulnerability detection accuracy across multiple programming languages.

AgentDID: Trustless Identity Authentication for AI Agents

The paper proposes AgentDID, a decentralized framework using DIDs and verifiable credentials to provide trustless identity authentication and dynamic state verification for autonomous, self-managed AI agents.

PRAG: End-to-End Privacy-Preserving Retrieval-Augmented Generation

PRAG is an end-to-end privacy-preserving Retrieval-Augmented Generation (RAG) system that maintains high retrieval accuracy and scalability in cloud environments by encrypting both documents and queries.

OrbitBFT: Enabling Scalable and Robust BFT Consensus in LEO Constellations

OrbitBFT introduces a novel two-stage hierarchical BFT consensus protocol that enables scalable and robust Byzantine Fault-Tolerant coordination for large-scale Low Earth Orbit satellite constellations.

Highlighted terms show continued research focus across papers

Papers

cs.DCcs.CRRecentMay 1, 2026

OrbitBFT: Enabling Scalable and Robust BFT Consensus in LEO Constellations

Tianyi Sun, Shuo Liu, Minghui Xu, Xiuzhen Cheng

OrbitBFT introduces a novel two-stage hierarchical BFT consensus protocol that enables scalable and robust Byzantine Fault-Tolerant coordination for large-scale Low Earth Orbit satellite constellation…

View →
cs.CRRecentApr 29, 2026

PRAG: End-to-End Privacy-Preserving Retrieval-Augmented Generation

Zhijun Li, Minghui Xu, Huayi Qi, Wenxuan Yu +5 more

PRAG is an end-to-end privacy-preserving Retrieval-Augmented Generation (RAG) system that maintains high retrieval accuracy and scalability in cloud environments by encrypting both documents and queri…

View →
cs.CRRecentApr 28, 2026

AgentDID: Trustless Identity Authentication for AI Agents

Minghui Xu, Xiaoyu Liu, Yihao Guo, Chunchi Liu +2 more

The paper proposes AgentDID, a decentralized framework using DIDs and verifiable credentials to provide trustless identity authentication and dynamic state verification for autonomous, self-managed AI…

View →
cs.CRRecentApr 21, 2026

SAGE: Signal-Amplified Guided Embeddings for LLM-based Vulnerability Detection

Zhengyang Shan, Xu Qian, Jiayun Xin, Minghui Xu +4 more

The paper proposes SAGE, a framework that uses Signal-Amplified Guided Embeddings to overcome 'Signal Submersion' in LLMs, significantly boosting vulnerability detection accuracy across multiple progr…

View →
cs.LGcs.CRRecentMar 20, 2026

Graph-Aware Stealthy Poison-Text Backdoors for Text-Attributed Graphs

Qi Luo, Minghui Xu, Dongxiao Yu, Xiuzhen Cheng

The paper proposes TAGBD, a graph-aware backdoor attack that demonstrates that inconspicuous poison text alone can reliably compromise text-attributed graph learning systems.

View →