mlsanityData to 14 Oct 2026

Fingerprinting Multimodal Large Language Models

arXiv 2609.20457 ↗First posted 17 Sep 2026cs.CR cs.AIcited by 0

On the map: Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness also fits: MLLM training and visual instruction tuning

Abstract (arXiv)

While multimodal large language models (MLLMs) enable a wide range of image-text reasoning tasks, recent incidents indicate that they are vulnerable to illicit deployment and unauthorized distillation. Existing solutions for model provenance are typically confounded by shared language backbones in MLLMs and struggle to detect violations of distillation. To bridge this gap and safeguard model ownership, we present the first study on multimodal model fingerprinting. Inspired by recent findings that self-attention acts as a low-pass filter and that its low-frequency components are informative, we develop AttnPrint for white-box provenance. Specifically, we extract cross-modal attention distributions and isolate their low-frequency components to serve as model fingerprints. To facilitate black-box auditing, we further introduce DistillTrace, which employs hypothesis testing of MLLM outputs to identify potential model infringement. We conduct extensive experiments on 154 model instances across 19 multimodal architectures. Notably, AttnPrint achieves strong derivative-model detection performance while remaining robust to five downstream modification techniques. DistillTrace also provides evidence of distillation relationships under three parameter-independent techniques.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 27 of its 46 references that are in the map. First posted on arXiv 17 Sep 2026.

Builds on

27 of 46 references.

References · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2025Qwen2.5-VL Technical Reportcited by 5,587
  5. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  6. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  7. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  8. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,396
  9. 2018Hierarchical Neural Story Generationcited by 1,193
  10. 2023A Simple and Effective Pruning Approach for Large Language Modelscited by 800
  11. 2024The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructionscited by 493
  12. 2025GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learningcited by 466
15 more
  1. 2025Kimi-VL Technical Reportcited by 388
  2. 2024ShortGPT: Layers in Large Language Models are More Redundant Than You Expectcited by 383
  3. 2022Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoningcited by 350
  4. 2019Connecting Vision and Language with Localized Narrativescited by 226
  5. 2024Building and better understanding vision-language models: insights and future directionscited by 173
  6. 2023MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuningcited by 150
  7. 2023On the Learnability of Watermarks for Language Modelscited by 81
  8. 2024Model Equality Testing: Which Model Is This API Serving?cited by 47
  9. 2024TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identificationcited by 36
  10. 2024FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Modelscited by 27
  11. 2025Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?cited by 19
  12. 2025Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model!cited by 18
  13. 2025SoK: Large Language Model Copyright Auditing via Fingerprintingcited by 15
  14. 2025Gradient-Based Model Fingerprinting for LLM Similarity Detection and Family Classificationcited by 14
  15. 2026Detecting Contextual Hallucinations in LLMs with Frequency-Aware Attentioncited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026AttnDiff: Attention-based Differential Fingerprinting for Large Language Models
  2. 2026A Behavioral Fingerprint for Large Language Models: Provenance Tracking via Refusal Vectors
  3. 2024Multimodal Large Language Models to Support Real-World Fact-Checking
  4. 2025Can GPT tell us why these images are synthesized? Empowering Multimodal Large Language Models for Forensics
  5. 2025Fingerprinting LLMs via Prompt Injection
  6. 2025EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic Fingerprint
  7. 2024MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models
  8. 2024MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models