Yushun Dong
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
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 is an inference-time framework that uses graph-based evidence routing to independently assess and repair unsupported facts (hallucinations) in multimodal generation.
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.
Papers
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 distribut…