# AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language Models

arXiv: https://arxiv.org/abs/2511.11299 · HTML: https://mlsanity.com/paper/2511.11299/

## 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 26 of its 32 references that are in the map.
- First posted on arXiv 14 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)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [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)
- [Who's Harry Potter? Approximate Unlearning in LLMs](https://mlsanity.com/paper/2310.02238/) (2023)
- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023)
- [In-Context Unlearning: Language Models as Few Shot Unlearners](https://mlsanity.com/paper/2310.07579/) (2023)
- [Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2405.15234/) (2024)
- [Towards Safer Large Language Models through Machine Unlearning](https://mlsanity.com/paper/2402.10058/) (2024)
- [Large Language Model Unlearning via Embedding-Corrupted Prompts](https://mlsanity.com/paper/2406.07933/) (2024)
- [Soft Prompting for Unlearning in Large Language Models](https://mlsanity.com/paper/2406.12038/) (2024)
- [CLEAR: Character Unlearning in Textual and Visual Modalities](https://mlsanity.com/paper/2410.18057/) (2024)
- [On Effects of Steering Latent Representation for Large Language Model Unlearning](https://mlsanity.com/paper/2408.06223/) (2024)
- [Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning](https://mlsanity.com/paper/2403.16257/) (2024)
- [From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks](https://mlsanity.com/paper/2407.02855/) (2024)
- [RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Models](https://mlsanity.com/paper/2406.01983/) (2024)
- [Extracting Unlearned Information from LLMs with Activation Steering](https://mlsanity.com/paper/2411.02631/) (2024)
- [Adversarial Machine Unlearning](https://mlsanity.com/paper/2406.07687/) (2024)
- [REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space](https://mlsanity.com/paper/2406.09325/) (2024)
- [Adversarial Mixup Unlearning](https://mlsanity.com/paper/2502.10288/) (2025)
- [Does Machine Unlearning Truly Remove Knowledge?](https://mlsanity.com/paper/2505.23270/) (2025)
- [Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats](https://mlsanity.com/paper/2409.19526/) (2024)
- [Attack and Reset for Unlearning: Exploiting Adversarial Noise toward Machine Unlearning through Parameter Re-initialization](https://mlsanity.com/paper/2401.08998/) (2024)
- [Soft Token Attacks Cannot Reliably Audit Unlearning in Large Language Models](https://mlsanity.com/paper/2502.15836/) (2025)
- [AMUN: Adversarial Machine UNlearning](https://mlsanity.com/paper/2503.00917/) (2025)

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

- [Visual-Guided Key-Token Regularization for Multimodal Large Language Model Unlearning](https://mlsanity.com/paper/2601.22020/) (2026)
- [Suppression Is Not Forgetting: Residual Recoverability in Visual Concept Unlearning for VLMs](https://mlsanity.com/paper/2604.03114/) (2026)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) achieve impressive performance once optimized on massive datasets. Such datasets often contain sensitive or copyrighted content, raising significant data privacy concerns. Regulatory frameworks mandating the 'right to be forgotten' drive the need for machine unlearning. This technique allows for the removal of target data without resource-consuming retraining. However, while well-studied for text, visual concept unlearning in MLLMs remains underexplored. A primary challenge is precisely removing a target visual concept without disrupting model performance on related entities. To address this, we introduce AUVIC, a novel visual concept unlearning framework for MLLMs. AUVIC applies adversarial perturbations to enable precise forgetting. This approach effectively isolates the target concept while avoiding unintended effects on similar entities. To evaluate our method, we construct VCUBench. It is the first benchmark designed to assess visual concept unlearning in group contexts. Experimental results demonstrate that AUVIC achieves state-of-the-art target forgetting rates while incurs minimal performance degradation on non-target concepts.