paper-with-me

Papers

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

2024-06-12 · Yu-Hsiang Huang, YuChe Tsai, Hsiang Hsiao, Hong-Yi Lin, Shou-De Lin

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. This approach uses a surrogate model to mimic the victim model's behavior, allowing the attacker to infer sensitive information from text embeddings without direct access. Our experiments across various embedding models and a clinical dataset demonstrate that our transfer attack significantly outperforms traditional methods, revealing the potential privacy vulnerabilities in embedding technologies and emphasizing the need for enhanced security measures.

📄 PDF Abstract BibTeX arXiv:2406.10280

Code (1)

coffree0123/TEIA 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion Attacks

2024-08-21 · Yiyi Chen, Russa Biswas, Heather Lent, Johannes Bjerva

Large Language Models (LLMs) are susceptible to malicious influence by cyber attackers through intrusions such as adversarial, backdoor, and embedding inversion attacks. In response, the burgeoning field of LLM Security …

All

Concept-Aware Privacy Mechanisms for Defending Embedding Inversion Attacks

2026-02-06 · Yu-Che Tsai, Hsiang Hsiao, Kuan-Yu Chen, Shou-De Lin arxiv

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 assum…

Uncovering Gradient Inversion Risks in Practical Language Model Training

2025-07-28 · Xinguo Feng, Zhongkui Ma, Zihan Wang, Eu Joe Chegne 외 arxiv

The gradient inversion attack has been demonstrated as a significant privacy threat to federated learning (FL), particularly in continuous domains such as vision models. In contrast, it is often considered less effective…

Federated Learning

DiffUMI: Training-Free Universal Model Inversion via Unconditional Diffusion for Face Recognition

2025-04-25 · Hanrui Wang, Shuo Wang, Chun-Shien Lu, Isao Echizen

Face recognition technology presents serious privacy risks due to its reliance on sensitive and immutable biometric data. To address these concerns, such systems typically convert raw facial images into embeddings, which…

Face GenerationFace RecognitionImage GenerationPrivacy Preserving+1

Denoising-Aware Inversion: Revealing Privacy Risks in Noise-Protected Text Embeddings

2026-08-19 · Yubo Wang, Shujie Cui, James Bailey, Hongzhi Yin 외 arxiv

Dense text embeddings are widely used in data mining, retrieval, and downstream machine learning systems due to their compact and semantically rich representations, but recent embedding inversion attacks have shown that …