🤖 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.
📝 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.