CBV generates clean-label poisoned samples for VLMs using diffusion models with score modification, multimodal guidance, and GradCAM-guided masks, achieving over 80% attack success rate on MSCOCO and VQA v2 while preserving normal functionality.
Proceedings of CVPR , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CBV: Clean-label Backdoor Attacks on Vision Language Models via Diffusion Models
CBV generates clean-label poisoned samples for VLMs using diffusion models with score modification, multimodal guidance, and GradCAM-guided masks, achieving over 80% attack success rate on MSCOCO and VQA v2 while preserving normal functionality.