PriMod4AI: Lifecycle-Aware Privacy Threat Modeling for AI Systems using LLM

📅 2026-02-04
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses the evolving privacy threats faced by AI systems throughout their lifecycle, which encompass both traditional risks and emerging model-centric attacks—such as membership inference and model inversion—that existing frameworks like LINDDUN fail to comprehensively cover. To bridge this gap, the authors propose a hybrid modeling paradigm that integrates LINDDUN with a knowledge base of AI-specific attacks. By leveraging metadata from data flow diagrams, semantic retrieval via a vector database, and data flow–aware prompt engineering, the approach guides large language models to perform lifecycle-aware, knowledge-driven, and interpretable privacy threat identification and classification. Empirical evaluation demonstrates that the method not only covers all classical privacy threat categories but also effectively detects model-centric attacks, yielding consistent and knowledge-grounded outputs across different large language models.

Technology Category

Application Category

📝 Abstract
Artificial intelligence systems introduce complex privacy risks throughout their lifecycle, especially when processing sensitive or high-dimensional data. Beyond the seven traditional privacy threat categories defined by the LINDDUN framework, AI systems are also exposed to model-centric privacy attacks such as membership inference and model inversion, which LINDDUN does not cover. To address both classical LINDDUN threats and additional AI-driven privacy attacks, PriMod4AI introduces a hybrid privacy threat modeling approach that unifies two structured knowledge sources, a LINDDUN knowledge base representing the established taxonomy, and a model-centric privacy attack knowledge base capturing threats outside LINDDUN. These knowledge bases are embedded into a vector database for semantic retrieval and combined with system level metadata derived from Data Flow Diagram. PriMod4AI uses retrieval-augmented and Data Flow specific prompt generation to guide large language models (LLMs) in identifying, explaining, and categorizing privacy threats across lifecycle stages. The framework produces justified and taxonomy-grounded threat assessments that integrate both classical and AI-driven perspectives. Evaluation on two AI systems indicates that PriMod4AI provides broad coverage of classical privacy categories while additionally identifying model-centric privacy threats. The framework produces consistent, knowledge-grounded outputs across LLMs, as reflected in agreement scores in the observed range.
Problem

Research questions and friction points this paper is trying to address.

privacy threat modeling
AI systems
model-centric attacks
LINDDUN
lifecycle-aware
Innovation

Methods, ideas, or system contributions that make the work stand out.

privacy threat modeling
LLM
retrieval-augmented generation
model-centric attacks
lifecycle-aware
G
Gautam Savaliya
Deggendorf Institute of Technology, Germany
R
Robert Aufschlager
Deggendorf Institute of Technology, Germany
A
Abhishek Subedi
Deggendorf Institute of Technology, Germany
M
Michael Heigl
Deggendorf Institute of Technology, Germany
M
Martin Schramm
Deggendorf Institute of Technology, Germany