Author

Ya-Li Yuan

h-index 4 View on Semantic Scholar

We have 2 of 25 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing

Fine-tuning-as-a-service enables users to adapt aligned large language models (LLMs) to specialized tasks, but malicious fine-tuning can erode refusal behavior while preserving task performance on legitimate inputs. We revisit recent layer-wise safety diagnostics and find that safety sensitivity is signed: scaling diff...

Hui Zhang, Ya-Chao Yuan, Jia-Yu Wang et al. · 0 citations

Open access Jun 2026

Optimizing multi-objective strategies for enhanced Tor De-anonymization

This work model joint node–technique selection as a tri-objective problem balancing attack gain (AP), attack impact (AI), and attack cost (AC) and selects a preference-aware compromise with VIKOR to support better de‑anonymization.

Yali Yuan, Yuchen Zhang, Ruolin Ma et al. · Cybersecurity · 0 citations