Trustworthy AI: Securing Sensitive Data in Large Language Models
- URL: http://arxiv.org/abs/2409.18222v1
- Date: Thu, 26 Sep 2024 19:02:33 GMT
- Title: Trustworthy AI: Securing Sensitive Data in Large Language Models
- Authors: Georgios Feretzakis, Vassilios S. Verykios,
- Abstract summary: Large Language Models (LLMs) have transformed natural language processing (NLP) by enabling robust text generation and understanding.
This paper proposes a comprehensive framework for embedding trust mechanisms into LLMs to dynamically control the disclosure of sensitive information.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large Language Models (LLMs) have transformed natural language processing (NLP) by enabling robust text generation and understanding. However, their deployment in sensitive domains like healthcare, finance, and legal services raises critical concerns about privacy and data security. This paper proposes a comprehensive framework for embedding trust mechanisms into LLMs to dynamically control the disclosure of sensitive information. The framework integrates three core components: User Trust Profiling, Information Sensitivity Detection, and Adaptive Output Control. By leveraging techniques such as Role-Based Access Control (RBAC), Attribute-Based Access Control (ABAC), Named Entity Recognition (NER), contextual analysis, and privacy-preserving methods like differential privacy, the system ensures that sensitive information is disclosed appropriately based on the user's trust level. By focusing on balancing data utility and privacy, the proposed solution offers a novel approach to securely deploying LLMs in high-risk environments. Future work will focus on testing this framework across various domains to evaluate its effectiveness in managing sensitive data while maintaining system efficiency.
Related papers
- AI-Driven Secure Data Sharing: A Trustworthy and Privacy-Preserving Approach [1.4274471390400758]
This research introduces a secure framework consisting of a learnable encryption method based on the block-pixel operation to encrypt the data.
The proposed framework ensures data privacy and security by creating unique scrambling patterns per key.
The framework was validated with a 94% success rate after extensive testing on real-world datasets.
arXiv Detail & Related papers (2025-01-26T02:03:19Z) - Deploying Privacy Guardrails for LLMs: A Comparative Analysis of Real-World Applications [3.1810537478232406]
OneShield is a framework designed to mitigate privacy risks in user inputs and LLM outputs across enterprise and open-source settings.
We analyze two real-world deployments, focusing on enterprise-scale data governance.
OneShield achieved a 0.95 F1 score in detecting sensitive entities across 26 languages, outperforming state-of-the-art tools.
arXiv Detail & Related papers (2025-01-21T19:04:53Z) - Powering LLM Regulation through Data: Bridging the Gap from Compute Thresholds to Customer Experiences [0.0]
This paper argues that current regulatory approaches, which focus on compute-level thresholds and generalized model evaluations, are insufficient to ensure the safety and effectiveness of specific LLM-based user experiences.
We propose a shift towards a certification process centered on actual user-facing experiences and the curation of high-quality datasets for evaluation.
arXiv Detail & Related papers (2025-01-12T16:20:40Z) - Privacy-Preserving Customer Support: A Framework for Secure and Scalable Interactions [0.0]
This paper introduces the Privacy-Preserving Zero-Shot Learning (PP-ZSL) framework, a novel approach leveraging large language models (LLMs) in a zero-shot learning mode.
Unlike conventional machine learning methods, PP-ZSL eliminates the need for local training on sensitive data by utilizing pre-trained LLMs to generate responses directly.
The framework incorporates real-time data anonymization to redact or mask sensitive information, retrieval-augmented generation (RAG) for domain-specific query resolution, and robust post-processing to ensure compliance with regulatory standards.
arXiv Detail & Related papers (2024-12-10T17:20:47Z) - Towards Secure and Private AI: A Framework for Decentralized Inference [14.526663289437584]
Large multimodal foundational models present challenges in scalability, reliability, and potential misuse.
Decentralized systems offer a solution by distributing workload and mitigating central points of failure.
We address these challenges with a comprehensive framework designed for responsible AI development.
arXiv Detail & Related papers (2024-07-28T05:09:17Z) - 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) - Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning [62.224804688233]
differential privacy (DP) offers a promising solution by ensuring models are 'almost indistinguishable' with or without any particular privacy unit.
We study user-level DP motivated by applications where it necessary to ensure uniform privacy protection across users.
arXiv Detail & Related papers (2024-06-20T13:54:32Z) - Decentralized Stochastic Optimization with Inherent Privacy Protection [103.62463469366557]
Decentralized optimization is the basic building block of modern collaborative machine learning, distributed estimation and control, and large-scale sensing.
Since involved data, privacy protection has become an increasingly pressing need in the implementation of decentralized optimization algorithms.
arXiv Detail & Related papers (2022-05-08T14:38:23Z) - Distributed Machine Learning and the Semblance of Trust [66.1227776348216]
Federated Learning (FL) allows the data owner to maintain data governance and perform model training locally without having to share their data.
FL and related techniques are often described as privacy-preserving.
We explain why this term is not appropriate and outline the risks associated with over-reliance on protocols that were not designed with formal definitions of privacy in mind.
arXiv Detail & Related papers (2021-12-21T08:44:05Z) - Trustworthy AI [75.99046162669997]
Brittleness to minor adversarial changes in the input data, ability to explain the decisions, address the bias in their training data, are some of the most prominent limitations.
We propose the tutorial on Trustworthy AI to address six critical issues in enhancing user and public trust in AI systems.
arXiv Detail & Related papers (2020-11-02T20:04:18Z) - CryptoSPN: Privacy-preserving Sum-Product Network Inference [84.88362774693914]
We present a framework for privacy-preserving inference of sum-product networks (SPNs)
CryptoSPN achieves highly efficient and accurate inference in the order of seconds for medium-sized SPNs.
arXiv Detail & Related papers (2020-02-03T14:49:18Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.