Author

Hong-Sheng Hu

h-index 2 View on Semantic Scholar

We have 3 of 7 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.

Sep 2026

CALM: Fine-grained federated unlearning via CLIP-assisted LoRA-MoE memory editing.

Federated learning (FL) enables decentralized clients to collaboratively train a global model without sharing raw data, inherently improving data confidentiality during training. With regulatory frameworks such as the General Data Protection Regulation (GDPR) mandating the right to be forgotten, Federated Unlearning (F...

Mang Su, Yang Bai, Cai-Yun Liu et al. · Neural Networks · 0 citations

Jul 2026

From Multiplicity to Vulnerability: Privacy Amplification Risk from One-Dataset-Multiple-Model Exposure

This work establishes a theoretical framework that proves that privacy leakage accumulates as more ODMM models are exposed, and proposes PRIME (Privacy Amplification RIsk from One-Dataset-Multiple-Model Exposure) to systematically assess this risk and quantify the resulting leakage using membership inference attacks (M...

Qirui Huang, Na Li, Hong-Sheng Hu et al. · arXiv.org · 0 citations

Jul 2026

When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training

This work reveals, for the first time, that RSMT can substantially amplify privacy leakage of these real training samples, and proposes a lightweight leakage propensity indicator computable from real data alone that reliably identifies high-risk datasets unsuitable for entering RSMT, as a self-assessable mitigation.

Na Li, Boyu Kuang, Hongsheng Hu et al. · arXiv.org · 0 citations