# Erase Persona, Forget Lore: Benchmarking Multimodal Copyright Unlearning in Large Vision Language Models

arXiv: https://arxiv.org/abs/2605.03547 · HTML: https://mlsanity.com/paper/2605.03547/

## Key facts

- Cited by 2 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 34 of its 52 references that are in the map.
- First posted on arXiv 5 May 2026.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)
- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 30 of 34)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning](https://mlsanity.com/paper/2403.03218/) (2024)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models](https://mlsanity.com/paper/2212.03860/) (2022)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [Trusting Your Evidence: Hallucinate Less with Context-aware Decoding](https://mlsanity.com/paper/2305.14739/) (2023)
- [Unrolling SGD: Understanding Factors Influencing Machine Unlearning](https://mlsanity.com/paper/2109.13398/) (2021)
- [MUSE: Machine Unlearning Six-Way Evaluation for Language Models](https://mlsanity.com/paper/2407.06460/) (2024)
- [Approximate Data Deletion from Machine Learning Models](https://mlsanity.com/paper/2002.10077/) (2020)
- [Influence Functions in Deep Learning Are Fragile](https://mlsanity.com/paper/2006.14651/) (2020)
- [Understanding and Mitigating Copying in Diffusion Models](https://mlsanity.com/paper/2305.20086/) (2023)
- [LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Model](https://mlsanity.com/paper/2401.02330/) (2024)
- [Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation](https://mlsanity.com/paper/2502.14846/) (2025)
- [Scalable Vision Language Model Training via High Quality Data Curation](https://mlsanity.com/paper/2501.05952/) (2025)
- [CLEAR: Character Unlearning in Textual and Visual Modalities](https://mlsanity.com/paper/2410.18057/) (2024)
- [CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation](https://mlsanity.com/paper/2407.07087/) (2024)
- [Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon](https://mlsanity.com/paper/2406.17746/) (2024)
- [The European Union general data protection regulation: what it is and what it means](https://mlsanity.com/paper/2510.02861/) (2025)
- [Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset](https://mlsanity.com/paper/2411.03554/) (2024)
- [Exploring Memorization and Copyright Violation in Frontier LLMs: A Study of the New York Times v. OpenAI 2023 Lawsuit](https://mlsanity.com/paper/2412.06370/) (2024)

## Built on by (most cited first, 2 of 2)

- [Open-MMUnlearning: Unifying Methods and Evaluation for MLLM Unlearning](https://mlsanity.com/paper/2610.10358/) (2026)
- [CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation](https://mlsanity.com/paper/2610.14763/) (2026)

## Abstract (arXiv)

Large Vision-Language Models (LVLMs), trained on web-scale data, risk memorizing and regenerating copyrighted visual content such as characters and logos, creating significant challenges. Machine unlearning offers a path to mitigate these risks by removing specific content post-training, but evaluating its effectiveness, especially in the complex multimodal setting of LVLMs, remains an open problem. Current evaluation methods often lack robustness or fail to capture the nuances of cross-modal concept erasure. To address this critical gap, we introduce the CoVUBench benchmark, the first framework specifically designed for evaluating copyright content unlearning in LVLMs. CoVUBench utilizes procedurally generated, legally safe synthetic data coupled with systematic visual variations spanning compositional changes and diverse domain manifestations to ensure realistic and robust evaluation of unlearning generalization. Our comprehensive multimodal evaluation protocol assesses both forgetting efficacy from the copyright holder perspective and the preservation of general model utility from the deployer viewpoint. By rigorously measuring this crucial trade-off, CoVUBench provides a standardized tool to advance the development of responsible and effective unlearning methods for LVLMs.