paper-with-me

홈 › Papers

Learning Obfuscations Of LLM Embedding Sequences: Stained Glass Transform

2025-06-11 · Jay Roberts, Kyle Mylonakis, Sidhartha Roy, Kaan Kale

The high cost of ownership of AI compute infrastructure and challenges of robust serving of large language models (LLMs) has led to a surge in managed Model-as-a-service deployments. Even when enterprises choose on-premises deployments, the compute infrastructure is typically shared across many teams in order to maximize the return on investment. In both scenarios the deployed models operate only on plaintext data, and so enterprise data owners must allow their data to appear in plaintext on a shared or multi-tenant compute infrastructure. This results in data owners with private or sensitive data being hesitant or restricted in what data they use with these types of deployments. In this work we introduce the Stained Glass Transform, a learned, stochastic, and sequence dependent transformation of the word embeddings of an LLM which information theoretically provides privacy to the input of the LLM while preserving the utility of model. We theoretically connect a particular class of Stained Glass Transforms to the theory of mutual information of Gaussian Mixture Models. We then calculate a-postiori privacy estimates, based on mutual information, and verify the privacy and utility of instances of transformed embeddings through token level metrics of privacy and standard LLM performance benchmarks.

📄 PDF Abstract BibTeX arXiv:2506.09452

Code (0)

등록된 구현이 없습니다.

Tasks

Word Embeddings

Similar Papers 제목 키워드 기반

Hierarchical Transformers Are More Efficient Language Models

2021-10-26 · Findings (NAACL) 2022 7 · Piotr Nawrot, Szymon Tworkowski, Michał Tyrolski, Łukasz Kaiser 외

Transformer models yield impressive results on many NLP and sequence modeling tasks. Remarkably, Transformers can handle long sequences which allows them to produce long coherent outputs: full paragraphs produced by GPT-…

Image GenerationLanguage ModelingLanguage Modelling

Hierarchical Transformers Are More Efficient Language Models

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Transformer models yield impressive results on many NLP and sequence modeling tasks. Remarkably, Transformers can handle long sequences, which allows them to produce long coherent outputs: entire paragraphs produced by G…

Language ModelingLanguage Modelling

Plentiful Jailbreaks with String Compositions

2024-11-01 · Brian R. Y. Huang

Large language models (LLMs) remain vulnerable to a slew of adversarial attacks and jailbreaking methods. One common approach employed by white-hat attackers, or red-teamers, is to process model inputs and outputs using …

Multi-view Spectral Polarization Propagation for Video Glass Segmentation

2023-01-01 · ICCV 2023 1 · Yu Qiao, Bo Dong, Ao Jin, Yu Fu 외

In this paper, we present the first polarization-guided video glass segmentation propagation solution (PGVS-Net) that can robustly and coherently propagate glass segmentation in RGB-P video sequences. By leveraging s…

Image SegmentationSegmentationSemantic Segmentation

Revisiting the Shape Convention of Transformer Language Models

2026-02-06 · Feng-Ting Liao, Meng-Hsi Chen, Guan-Ting Yi, Da-shan Shiu arxiv

The architectural shape of dense Transformers has remained remarkably stable: narrow-wide-narrow feed-forward networks (FFNs) consume most non-embedding parameters. Motivated by theoretical and empirical evidences that r…