A LINDDUN-based Privacy Threat Modeling Framework for GenAI

TL;DR

This paper develops a privacy threat modeling framework based on LINDDUN tailored for GenAI systems, addressing unique privacy challenges and expanding threat types with new examples, validated through a case study.

Contribution

It introduces a novel GenAI-specific privacy threat modeling framework based on LINDDUN, incorporating new threat types and examples, and demonstrates its effectiveness through validation.

Findings

Framework supports comprehensive privacy analysis of GenAI systems.

Three of seven LINDDUN privacy threats are extended for GenAI.

100 new GenAI privacy threat examples are added to the knowledge base.

Abstract

As generative AI (GenAI) systems become increasingly prevalent across various technological stacks, the question of how such systems handle sensitive and personal data flows becomes increasingly important. Specifically, both the ability to harness and process large swaths of information as well as their stochastic nature raise key concerns related to both security and privacy. Unfortunately, while some of the traditional security threat modeling can effectively identify certain violations, privacy-related issues are often overlooked. To respond to these challenges, we introduce a novel domain-specific privacy threat modeling framework to support the privacy threat analysis of GenAI-based applications. This framework is constructed through a two-pronged approach: (1) a systematic review of the emerging literature on GenAI privacy threats, and (2) a case-driven application to a representative Chatbot system. These efforts yield a foundational GenAI privacy threat modeling framework built on LINDDUN. The new framework affects three out of the seven privacy threat types of LINDDUN and introduces 100 new GenAI examples to the knowledge base. Its effectiveness is validated on an AI Agent system, which demonstrates that a comprehensive privacy analysis can be supported by the new framework.