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.
Ieee Access , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 3roles
method 1polarities
use method 1representative citing papers
ATAAT is an adaptive adversarial tuning method that enables effective, stealthy backdoor attacks on VLA models by dynamically selecting gradient decoupling strategies based on attacker capabilities.
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.
-
ATAAT: Adaptive Threat-Aware Adversarial Tuning Framework against Backdoor Attacks on Vision-Language-Action Models
ATAAT is an adaptive adversarial tuning method that enables effective, stealthy backdoor attacks on VLA models by dynamically selecting gradient decoupling strategies based on attacker capabilities.
- TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting