Goto

Collaborating Authors

 personal identifiable information


DePrompt: Desensitization and Evaluation of Personal Identifiable Information in Large Language Model Prompts

arXiv.org Artificial Intelligence

Prompt serves as a crucial link in interacting with large language models (LLMs), widely impacting the accuracy and interpretability of model outputs. However, acquiring accurate and high-quality responses necessitates precise prompts, which inevitably pose significant risks of personal identifiable information (PII) leakage. Therefore, this paper proposes DePrompt, a desensitization protection and effectiveness evaluation framework for prompt, enabling users to safely and transparently utilize LLMs. Specifically, by leveraging large model fine-tuning techniques as the underlying privacy protection method, we integrate contextual attributes to define privacy types, achieving high-precision PII entity identification. Additionally, through the analysis of key features in prompt desensitization scenarios, we devise adversarial generative desensitization methods that retain important semantic content while disrupting the link between identifiers and privacy attributes. Furthermore, we present utility evaluation metrics for prompt to better gauge and balance privacy and usability. Our framework is adaptable to prompts and can be extended to text usability-dependent scenarios. Through comparison with benchmarks and other model methods, experimental evaluations demonstrate that our desensitized prompt exhibit superior privacy protection utility and model inference results.


Cybersecurity: The Benefits and Threats of AI Technology

#artificialintelligence

Artificial intelligence (AI) is not "just around the corner" but here today and proceeding rapidly to change much about how we live and operate in a digital world. Like it or not ... it is here to stay! I got the following guest piece on the impacts of AI to cybersecurity and wanted to share it with you. One thing not mentioned in the piece is how AI will significantly reduce your workforce shortage of cybersecurity technicians. They will be needed, as is pointed out in the summary below, but not in the numbers they are projected to be needed in the coming years. Here's the piece -- which is a summary of an article by the author: Monica Oravcova, COO and co-founder of cybersecurity firm Naoris Protocol, on how AI affects cybersecurity.


Data Readiness for Natural Language Processing

arXiv.org Artificial Intelligence

This document concerns data readiness in the context of machine learning and Natural Language Processing. It describes how an organization may proceed to identify, make available, validate, and prepare data to facilitate automated analysis methods. The contents of the document is based on the practical challenges and frequently asked questions we have encountered in our work as an applied research institute with helping organizations and companies, both in the public and private sectors, to use data in their business processes.