Skip to main navigation Skip to search Skip to main content

Query-Based Fingerprinting of Text-to-Image Large Language Models

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The rapid adoption of text-to-image large language models (LLMs) has raised critical concerns regarding model attribution, accountability, and misuse, particularly as these models are frequently fine-tuned, modified, and redistributed. Existing attribution approaches, such as watermarking and semantic query-based methods, often fail under black-box settings or degrade when models undergo prompt variation and fine-tuning. In this paper, we propose a robust query-based fingerprinting framework for attributing text-to-image generating LLMs under realistic deployment conditions. The proposed method constructs a diverse set of discriminative prompts and compares images generated before and after model modification using ORB (Oriented FAST and Rotated BRIEF) feature matching. By focusing on low-level visual artifacts and training-induced patterns, the approach captures intrinsic model characteristics that persist across prompt transformations, fine-tuning, and contextual modifications. We evaluate the proposed method on multiple state-of-the-art text-to-image models under three challenging scenarios: input transformation, model fine-tuning, and prompt modification. Experimental results demonstrate that the method achieves approximately 97% attribution accuracy while operating entirely in a black-box setting and without embedding watermarks or accessing model internals. These findings highlight the effectiveness of the proposed approach for scalable and non-invasive model attribution in dynamic generative AI ecosystems.

Original languageEnglish
Title of host publicationProceedings - 2026 IEEE 12th Conference on Big Data Security on Cloud, BigDataSecurity 2026
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages54-59
Number of pages6
ISBN (Electronic)9798319532367
DOIs
StatePublished - 2026
Event12th IEEE International Conference on Big Data Security on Cloud, BigDataSecurity 2026 - New York, United States
Duration: May 8 2026 → May 10 2026

Publication series

NameProceedings - 2026 IEEE 12th Conference on Big Data Security on Cloud, BigDataSecurity 2026

Conference

Conference12th IEEE International Conference on Big Data Security on Cloud, BigDataSecurity 2026
Country/TerritoryUnited States
CityNew York
Period5/8/26 → 5/10/26

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Information Systems
  • Information Systems and Management
  • Safety, Risk, Reliability and Quality

Keywords

  • Model Attribution
  • Model Security
  • Query-based Fingerprinting
  • Text-to-Image Generation

Fingerprint

Dive into the research topics of 'Query-Based Fingerprinting of Text-to-Image Large Language Models'. Together they form a unique fingerprint.

Cite this