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

Qiang Hu

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Crypto×2Vision×1Software Eng.×1AI×1

Frequent co-authors

Lu Liu1×
Huiyu Duan1×
Chenxin Zhu1×
Jintong Lu1×
Haoyun Jiang1×
Liu Yang1×

Research Timeline

2026
E-MIA: Exam-Style Black-Box Membership Inference Attacks against RAG Systems

E-MIA introduces a novel, stealthy black-box membership inference attack that converts verifiable hard evidence within a candidate document into an objective, multi-part exam score to determine if the document was ingested into a RAG knowledge base.

Towards Demystifying and Repairing LLM-in-the-Loop Vulnerabilities

The paper addresses the gap in understanding real-world LLM-in-the-loop vulnerabilities by creating the LLMCVE dataset and demonstrating that these vulnerabilities are significantly harder to repair than conventional software flaws.

LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models

The paper introduces LL-Bench, a comprehensive benchmark for evaluating large-scale generative models on low-level vision tasks, and proposes LL-Score, an MLLM-based evaluator that better aligns quality assessment with human preferences.

Highlighted terms show continued research focus across papers

Papers

cs.CVRecentJun 1, 2026

LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models

Lu Liu, Huiyu Duan, Chenxin Zhu, Jintong Lu +5 more

The paper introduces LL-Bench, a comprehensive benchmark for evaluating large-scale generative models on low-level vision tasks, and proposes LL-Score, an MLLM-based evaluator that better aligns quali…

View →
cs.SEcs.CRRecentMay 27, 2026

Towards Demystifying and Repairing LLM-in-the-Loop Vulnerabilities

Yujie Ma, Jialin Rong, Chenxi Yang, Lili Quan +3 more

The paper addresses the gap in understanding real-world LLM-in-the-loop vulnerabilities by creating the LLMCVE dataset and demonstrating that these vulnerabilities are significantly harder to repair t…

View →
cs.CRcs.AIRecentMay 1, 2026

E-MIA: Exam-Style Black-Box Membership Inference Attacks against RAG Systems

Zelin Guan, Shengda Zhuo, Zeyan Li, Jinchun He +3 more

E-MIA introduces a novel, stealthy black-box membership inference attack that converts verifiable hard evidence within a candidate document into an objective, multi-part exam score to determine if the…

View →