Hsiang Hsiao — accepted AI-conference papers

2026

Concept-Aware Privacy Mechanisms for Defending Embedding Inversion Attacks

Yu-Che Tsai, Hsiang Hsiao, Kuan-Yu Chen, Shou-De Lin

ICLR 2026poster

Text embeddings enable numerous NLP applications but face severe privacy risks from embedding inversion attacks, which can expose sensitive attributes or reconstruct raw text. Existing differential privacy defenses assume uniform sensitivity across embedding dimensions, leading to excessive noise an…

Cited by 0 Source ↗Scholar ↗

2024

Transferable Embedding Inversion Attack: Uncovering Privacy Risks in Text Embeddings without Model Queries

Yu-Hsiang Huang, Yuche Tsai, Hsiang Hsiao, Hong-Yi Lin, Shou-De Lin

ACL 2024long

This study investigates the privacy risks associated with text embeddings, focusing on the scenario where attackers cannot access the original embedding model. Contrary to previous research requiring direct model access, we explore a more realistic threat model by developing a transfer attack method…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗