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

Yushun Dong

3 indexed papers

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

Publications per year

3
26

Top categories

Crypto×2AI×2ML×2NLP×1

Frequent co-authors

Kaixiang Zhao2×
Shuze Liu1×
Qianwen Guo1×
Tianrun Yu1×
Shawn Huang1×
Porter Jenkins1×

Research Timeline

2026
GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?

The paper introduces GraphIP-Bench, a unified benchmark that demonstrates that stealing Graph Neural Networks (GNNs) is relatively easy, and existing defenses often fail to maintain their integrity after the model is successfully extracted.

TIGER: Traceable Inference with Graph-Based Evidence Routing for Mitigating Hallucinations in Multimodal Generation

TIGER is an inference-time framework that uses graph-based evidence routing to independently assess and repair unsupported facts (hallucinations) in multimodal generation.

An Embarrassingly Simple Detector for Model Extraction Attacks in Large Language Model API Traffic

The paper proposes an embarrassingly simple detector that monitors model extraction attacks by testing whether the aggregate distribution of incoming LLM queries deviates from the historical distribution of benign traffic.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.CLRecentJun 4, 2026

An Embarrassingly Simple Detector for Model Extraction Attacks in Large Language Model API Traffic

Shuze Liu, Qianwen Guo, Yushun Dong

The paper proposes an embarrassingly simple detector that monitors model extraction attacks by testing whether the aggregate distribution of incoming LLM queries deviates from the historical distribut…

View →
cs.AIcs.LGRecentMay 29, 2026

TIGER: Traceable Inference with Graph-Based Evidence Routing for Mitigating Hallucinations in Multimodal Generation

Kaixiang Zhao, Tianrun Yu, Shawn Huang, Porter Jenkins +2 more

TIGER is an inference-time framework that uses graph-based evidence routing to independently assess and repair unsupported facts (hallucinations) in multimodal generation.

View →
cs.CRcs.AIcs.LGRecentMay 12, 2026

GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?

Kaixiang Zhao, Bolin Shen, Yuyang Dai, Shayok Chakraborty +1 more

The paper introduces GraphIP-Bench, a unified benchmark that demonstrates that stealing Graph Neural Networks (GNNs) is relatively easy, and existing defenses often fail to maintain their integrity af…

View →