mlsanityData to 14 Oct 2026

Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges

arXiv 2606.09125 ↗First posted 8 Jun 2026cs.CR cs.AIcited by 4

On the map: Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness

Abstract (arXiv)

Privacy risks in text-only Large Language Models (LLMs) are well studied, particularly their tendency to memorize and leak sensitive information. However, Multi-modal Large Language Models (MLLMs), which process both text and images, introduce unique privacy challenges that remain underexplored. Compared to text-only models, MLLMs can extract and expose sensitive information embedded in images, posing new privacy risks. We reveal that some MLLMs are susceptible to privacy breaches, leaking sensitive data embedded in images or stored in memory. Specifically, in this paper, we (1) introduce MM-Privacy, a comprehensive dataset designed to assess privacy risks across various multi-modal tasks and scenarios, where we define Disclosure Risks and Retention Risks. (2) systematically evaluate different MLLMs using MM-Privacy and demonstrate how models leak sensitive data across various tasks, and (3) provide additional insights into the role of task inconsistency in privacy risks, emphasizing the urgent need for mitigation strategies. Our findings highlight privacy concerns in MLLMs, underscoring the necessity of safeguards to prevent data exposure. Our dataset and code can be found here.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 13 of its 27 references that are in the map. First posted on arXiv 8 Jun 2026.

Builds on

13 of 27 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation14 Mar
  2. 2024AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting14 Mar
  3. 2024Safety of Multimodal Large Language Models on Images and Texts1 Feb
  4. 2024MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance5 Jan
  5. 2023FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts9 Nov
  6. 2023How Robust is Google's Bard to Adversarial Image Attacks?21 Sep

Other references · 7

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  4. 2020Extracting Training Data from Large Language Modelscited by 2,189
  5. 2022Are Large Pre-Trained Language Models Leaking Your Personal Information?cited by 200
  6. 2022Memorization in NLP Fine-tuning Methodscited by 45
  7. 2022Canary Extraction in Natural Language Understanding Modelscited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026TRAP: Benchmark for Task-completion and Resistance to Active Privacy-extractioncited by 1
  2. 2026Beyond Visual Evidence: Revealing and Mitigating Relational Privacy Leakage in Document MLLMscited by 0
  3. 2026Masking Is Not Enough: Generative Restoration for Multimodal De-Identification in Medical AIcited by 0
  4. 2026Text-Anchored Semantic Perturbations for Transferable Jailbreak Attacks on Multimodal Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on Privacy Risks and Protection in Large Language Models
  2. 2025Defeating Cerberus: Concept-Guided Privacy-Leakage Mitigation in Multimodal Language Models
  3. 2025SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation
  4. 2024Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions
  5. 2024Multi-PA: A Multi-perspective Benchmark on Privacy Assessment for Large Vision-Language Models
  6. 2025The Model's Language Matters: A Comparative Privacy Analysis of LLMs
  7. 2024Privacy-Preserving Large Language Models: Mechanisms, Applications, and Future Directions
  8. 2024Undesirable Memorization in Large Language Models: A Survey