AINeutralarXiv – CS AI · 6h ago6/10
🧠
Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction
Researchers introduce DeBias-Attack, a novel adversarial attack method that improves cross-model transferability on Vision-Language Pre-training models by correcting surrogate-specific bias in gradient optimization. The technique uses a dual-branch approach to distinguish between model-dependent artifacts and input semantics, demonstrating strong performance across multiple VLP systems and multimodal language models.