PriMod4AI: Lifecycle-Aware Privacy Threat Modeling for AI Systems using LLM
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910012034514944 |
|---|---|
| author | Savaliya, Gautam Aufschläger, Robert Subedi, Abhishek Heigl, Michael Schramm, Martin |
| author_facet | Savaliya, Gautam Aufschläger, Robert Subedi, Abhishek Heigl, Michael Schramm, Martin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_04927 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PriMod4AI: Lifecycle-Aware Privacy Threat Modeling for AI Systems using LLM Savaliya, Gautam Aufschläger, Robert Subedi, Abhishek Heigl, Michael Schramm, Martin Cryptography and Security Artificial Intelligence 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. |
| title | PriMod4AI: Lifecycle-Aware Privacy Threat Modeling for AI Systems using LLM |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2602.04927 |