mlsanityData to 7 Oct 2026

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

arXiv 2511.11299 ↗First posted 14 Nov 2025cs.CV cs.AIcited by 2

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

also in 1 more
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.

Key facts. Cited by 2 papers in the map (data through 7 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.

Builds on

26 of 32 references.

References · 26

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,881
  3. 2024TOFU: A Task of Fictitious Unlearning for LLMscited by 507
  4. 2024The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearningcited by 488
  5. 2024Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearningcited by 484
  6. 2023Who's Harry Potter? Approximate Unlearning in LLMscited by 366
  7. 2023Large Language Model Unlearningcited by 288
  8. 2023In-Context Unlearning: Language Models as Few Shot Unlearnerscited by 214
  9. 2024Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Modelscited by 164
  10. 2024Towards Safer Large Language Models through Machine Unlearningcited by 134
  11. 2024Large Language Model Unlearning via Embedding-Corrupted Promptscited by 112
  12. 2024Soft Prompting for Unlearning in Large Language Modelscited by 42
14 more
  1. 2024CLEAR: Character Unlearning in Textual and Visual Modalitiescited by 36
  2. 2024Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearningcited by 31
  3. 2024From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attackscited by 29
  4. 2024On Effects of Steering Latent Representation for Large Language Model Unlearningcited by 27
  5. 2024RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Modelscited by 21
  6. 2024Extracting Unlearned Information from LLMs with Activation Steeringcited by 19
  7. 2024Adversarial Machine Unlearningcited by 16
  8. 2024REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Spacecited by 12
  9. 2025Adversarial Mixup Unlearningcited by 7
  10. 2025Does Machine Unlearning Truly Remove Knowledge?cited by 7
  11. 2024Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threatscited by 6
  12. 2024Attack and Reset for Unlearning: Exploiting Adversarial Noise toward Machine Unlearning through Parameter Re-initializationcited by 5
  13. 2025Soft Token Attacks Cannot Reliably Audit Unlearning in Large Language Modelscited by 2
  14. 2025AMUN: Adversarial Machine UNlearningcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Visual-Guided Key-Token Regularization for Multimodal Large Language Model Unlearningcited by 3
  2. 2026Suppression Is Not Forgetting: Residual Recoverability in Visual Concept Unlearning for VLMscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models
  2. 2026Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning
  3. 2025MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering
  4. 2026Null Space Constrained Contrastive Visual Forgetting for MLLM Unlearning
  5. 2025PEBench: A Fictitious Dataset to Benchmark Machine Unlearning for Multimodal Large Language Models
  6. 2026ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition
  7. 2025MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models
  8. 2026Open-MMUnlearning: Unifying Methods and Evaluation for MLLM Unlearning