DBLP: Noise bridge consistency distillation for efficient and reliable adversarial purification

Recent advances in deep neural networks (DNNs) have led to remarkable success across a wide range of tasks. However, their susceptibility to adversarial perturbations remains a critical vulnerability. Existing diffusion-based adversarial purification methods often require intensive iterative denoising, severely limiting their practical deployment. In this paper, we propose Diffusion Bridge Distillation for Purification (DBLP), a novel and efficient diffusion-based framework for adversarial purification. Central to our approach is a new objective, noise bridge distillation, which constructs a principled alignment between the adversarial noise distribution and the clean data distribution within a latent consistency model (LCM). To further enhance semantic fidelity, we introduce adaptive semantic enhancement, which fuses multi-scale pyramid edge maps as conditioning input to guide the purification process. Extensive experiments across multiple datasets demonstrate that DBLP achieves state-of-the-art robust accuracy, outperforming prior methods by up to 7.20% on CIFAR-10 and 1.2% on ImageNet, with superior image quality, and approximately 0.2 s inference time, marking a significant step toward real-time adversarial purification that is both theoretically grounded and practically deployable across latency-sensitive real-world systems.