Related papers: Learning Obfuscations Of LLM Embedding Sequences: Stained Glass Transform

Learning Obfuscations Of LLM Embedding Sequences: Stained Glass Transform

URL: http://arxiv.org/abs/2506.09452v1
Date: Wed, 11 Jun 2025 06:56:12 GMT
Title: Learning Obfuscations Of LLM Embedding Sequences: Stained Glass Transform
Authors: Jay Roberts, Kyle Mylonakis, Sidhartha Roy, Kaan Kale,
Abstract summary: We introduce the Stained Glass Transform, a learned, sequence dependent transformation of the word embeddings of an AI model.<n>We calculate a-postiori privacy estimates, based on mutual information, and verify the privacy and utility of instances of transformed embeddings.
Score: 1.8749305679160366
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
Abstract: 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.

Related papers

Large Language Models are Good Relational Learners [55.40941576497973]
We introduce Rel-LLM, a novel architecture that utilizes a graph neural network (GNN)- based encoder to generate structured relational prompts for large language models (LLMs)<n>Unlike traditional text-based serialization approaches, our method preserves the inherent relational structure of databases while enabling LLMs to process and reason over complex entity relationships.
arXiv Detail & Related papers (2025-06-06T04:07:55Z)
LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization [59.75242204923353]
We introduce LLM-Lasso, a framework that leverages large language models (LLMs) to guide feature selection in Lasso regression.<n>LLMs generate penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model.<n>Features identified as more relevant by the LLM receive lower penalties, increasing their likelihood of being retained in the final model.
arXiv Detail & Related papers (2025-02-15T02:55:22Z)
Model Inversion in Split Learning for Personalized LLMs: New Insights from Information Bottleneck Theory [11.83473842859642]
This work is the first to identify model inversion attacks in the split learning framework for personalized LLMs.<n>We propose a two-stage attack system in which the first part projects representations into the embedding space, and the second part uses a generative model to recover text from these embeddings.
arXiv Detail & Related papers (2025-01-10T13:47:13Z)
Federated In-Context LLM Agent Learning [3.4757641432843487]
Large Language Models (LLMs) have revolutionized intelligent services by enabling logical reasoning, tool use, and interaction with external systems as agents.<n>In this paper, we propose a novel privacy-preserving Federated In-context LLM Agent Learning (FICAL) algorithm.<n>The results show that FICAL has competitive performance compared to other SOTA baselines with a significant communication cost decrease of $mathbf3.33times105$ times.
arXiv Detail & Related papers (2024-12-11T03:00:24Z)
Model-based Large Language Model Customization as Service [34.949731264918846]
Large Language Model (LLM) services from providers like OpenAI and Google excel at general tasks but often underperform on domain-specific applications.<n>We introduce Llamdex, a novel framework that facilitates LLM customization as a service, where the client uploads pre-trained domain-specific models rather than data.<n> Experiments demonstrate that Llamdex improves domain-specific accuracy by up to 26% over state-of-the-art private data synthesis methods under identical privacy constraints.
arXiv Detail & Related papers (2024-10-14T13:18:20Z)
LLM-PBE: Assessing Data Privacy in Large Language Models [111.58198436835036]
Large Language Models (LLMs) have become integral to numerous domains, significantly advancing applications in data management, mining, and analysis. Despite the critical nature of this issue, there has been no existing literature to offer a comprehensive assessment of data privacy risks in LLMs. Our paper introduces LLM-PBE, a toolkit crafted specifically for the systematic evaluation of data privacy risks in LLMs.
arXiv Detail & Related papers (2024-08-23T01:37:29Z)
HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection [44.225151701532454]
In this paper, we introduce a new framework HARMONIC for tabular data generation and evaluation. Our framework achieves equivalent performance to existing methods with better privacy, which also demonstrates our evaluation framework for the effectiveness of synthetic data and privacy risks.
arXiv Detail & Related papers (2024-08-06T03:21:13Z)
Robust Utility-Preserving Text Anonymization Based on Large Language Models [80.5266278002083]
Text anonymization is crucial for sharing sensitive data while maintaining privacy. Existing techniques face the emerging challenges of re-identification attack ability of Large Language Models. This paper proposes a framework composed of three LLM-based components -- a privacy evaluator, a utility evaluator, and an optimization component.
arXiv Detail & Related papers (2024-07-16T14:28:56Z)
Federated Domain-Specific Knowledge Transfer on Large Language Models Using Synthetic Data [53.70870879858533]
We introduce a Federated Domain-specific Knowledge Transfer framework. It enables domain-specific knowledge transfer from LLMs to SLMs while preserving clients' data privacy. The proposed FDKT framework consistently and greatly improves SLMs' task performance by around 5% with a privacy budget of less than 10.
arXiv Detail & Related papers (2024-05-23T06:14:35Z)
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models [52.98743860365194]
We propose a new fine-tuning method called Self-Play fIne-tuNing (SPIN) At the heart of SPIN lies a self-play mechanism, where the LLM refines its capability by playing against instances of itself. This sheds light on the promise of self-play, enabling the achievement of human-level performance in LLMs without the need for expert opponents.
arXiv Detail & Related papers (2024-01-02T18:53:13Z)
FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning [70.38817963253034]
This paper first discusses these challenges of federated fine-tuning LLMs, and introduces our package FS-LLM as a main contribution. We provide comprehensive federated parameter-efficient fine-tuning algorithm implementations and versatile programming interfaces for future extension in FL scenarios. We conduct extensive experiments to validate the effectiveness of FS-LLM and benchmark advanced LLMs with state-of-the-art parameter-efficient fine-tuning algorithms in FL settings.
arXiv Detail & Related papers (2023-09-01T09:40:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.