One Modality to Forget Them All: Enhancing Cross-Modal Unlearning in Vision-Language Models
Sudharshan Balaji, Yili Ren, Guangjing Wang, Yimin Chen, Ning Wang
cs.CV, cs.CL, cs.CR
Submitted: 2026-07-17
Comments: 18 pages
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions
- MultiDelete for Multimodal Machine Unlearning
- InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
- QLoRA: Efficient Finetuning of Quantized LLMs
- SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
- Erasing Concepts from Diffusion Models
- A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models
- COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset
- WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
- Improved Baselines with Visual Instruction Tuning
- Visual Instruction Tuning
- JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks
- TOFU: A Task of Fictitious Unlearning for LLMs
- Jailbroken: How Does LLM Safety Training Fail?
- Large Language Model Unlearning
- Catastrophic Failure of LLM Unlearning via Quantization
- Universal and Transferable Adversarial Attacks on Aligned Language Models
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models