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

Document Type

Article

Source of Publication

Computers and Electrical Engineering

Publication Date

12-1-2026

Abstract

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.

ISSN

0045-7906

Publisher

Elsevier BV

Volume

140

Disciplines

Computer Sciences

Keywords

Adversarial purification, AI security, Deep neural networks, Diffusion Bridge Distillation, Latent Consistency Model

Scopus ID

105050753812

Indexed in Scopus

yes

Open Access

yes

Open Access Type

Hybrid: This publication is openly available in a subscription-based journal/series

This document is currently not available here.

Share

COinS