# Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models

arXiv: https://arxiv.org/abs/2511.06793 · HTML: https://mlsanity.com/paper/2511.06793/

## Key facts

- Cited by 8 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 26 of its 37 references that are in the map.
- First posted on arXiv 10 Nov 2025.

## 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, 26 of 26)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [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)
- [Editing Large Language Models: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2305.13172/) (2023)
- [Unrolling SGD: Understanding Factors Influencing Machine Unlearning](https://mlsanity.com/paper/2109.13398/) (2021)
- [Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models](https://mlsanity.com/paper/2301.04213/) (2023)
- [Model Sparsity Can Simplify Machine Unlearning](https://mlsanity.com/paper/2304.04934/) (2023)
- [Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning](https://mlsanity.com/paper/2410.07163/) (2024)
- [Continual Learning and Private Unlearning](https://mlsanity.com/paper/2203.12817/) (2022)
- [Variational Bayesian Unlearning](https://mlsanity.com/paper/2010.12883/) (2020)
- [MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance](https://mlsanity.com/paper/2401.02906/) (2024)
- [Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench](https://mlsanity.com/paper/2410.22108/) (2024)
- [PUMA: Performance Unchanged Model Augmentation for Training Data Removal](https://mlsanity.com/paper/2203.00846/) (2022)
- [Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons](https://mlsanity.com/paper/2308.13198/) (2023)
- [CLEAR: Character Unlearning in Textual and Visual Modalities](https://mlsanity.com/paper/2410.18057/) (2024)
- [Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation](https://mlsanity.com/paper/2308.08090/) (2023)
- [SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning](https://mlsanity.com/paper/2502.12520/) (2025)
- [Analyzing And Editing Inner Mechanisms Of Backdoored Language Models](https://mlsanity.com/paper/2302.12461/) (2023)
- [CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP](https://mlsanity.com/paper/2410.23330/) (2024)
- [Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models](https://mlsanity.com/paper/2305.09144/) (2023)
- [Influence Patterns for Explaining Information Flow in BERT](https://mlsanity.com/paper/2011.00740/) (2020)
- [Discovering Influential Neuron Path in Vision Transformers](https://mlsanity.com/paper/2503.09046/) (2025)
- [Identifying Multi-modal Knowledge Neurons in Pretrained Transformers via Two-stage Filtering](https://mlsanity.com/paper/2503.22941/) (2025)

## Built on by (most cited first, 8 of 8)

- [EASE: Federated Multimodal Unlearning via Entanglement-Aware Anchor Closure](https://mlsanity.com/paper/2605.00733/) (2026)
- [Visual-Guided Key-Token Regularization for Multimodal Large Language Model Unlearning](https://mlsanity.com/paper/2601.22020/) (2026)
- [SGM: Safety Glasses for Multimodal Large Language Models via Neuron-Level Detoxification](https://mlsanity.com/paper/2512.15052/) (2025)
- [MemLeak: Diagnosing Information Leaks in Multimodal Agent Memory](https://mlsanity.com/paper/2606.29788/) (2026)
- [AIM: Anchor Identity Features, Then Match for Multimodal Large Language Model Unlearning](https://mlsanity.com/paper/2608.28312/) (2026)
- [SPACE: Source-free Proxy Anchor Concept Erasure for MLLMs](https://mlsanity.com/paper/2606.09868/) (2026)
- [SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning](https://mlsanity.com/paper/2610.01962/) (2026)
- [CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation](https://mlsanity.com/paper/2610.14763/) (2026)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) extend foundation models to real-world applications by integrating inputs such as text and vision. However, their broad knowledge capacity raises growing concerns about privacy leakage, toxicity mitigation, and intellectual property violations. Machine Unlearning (MU) offers a practical solution by selectively forgetting targeted knowledge while preserving overall model utility. When applied to MLLMs, existing neuron-editing-based MU approaches face two fundamental challenges: (1) forgetting becomes inconsistent across modalities because existing point-wise attribution methods fail to capture the structured, layer-by-layer information flow that connects different modalities; and (2) general knowledge performance declines when sensitive neurons that also support important reasoning paths are pruned, as this disrupts the model's ability to generalize. To alleviate these limitations, we propose a multimodal influential neuron path editor (MIP-Editor) for MU. Our approach introduces modality-specific attribution scores to identify influential neuron paths responsible for encoding forget-set knowledge and applies influential-path-aware neuron-editing via representation misdirection. This strategy also enables effective and coordinated forgetting across modalities while preserving the model's general capabilities. Experimental results demonstrate that MIP-Editor achieves a superior unlearning performance on multimodal tasks, with a maximum forgetting rate of 87.75% and up to 54.26% improvement in general knowledge retention. On textual tasks, MIP-Editor achieves up to 80.65% forgetting and preserves 77.9% of general performance. Codes are available at https://github.com/PreckLi/MIP-Editor.