Fuyi Wang
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1NLP×1ML×1
Frequent co-authors
Research Timeline
2026
What Does the Server See? Understanding Privacy Leakage from Large Language Models in Split Inference
The paper introduces ActInv and PAF to systematically analyze and quantify privacy leakage from intermediate activations during split inference of LLMs, proposing PriPert for enhanced defense.
Highlighted terms show continued research focus across papers