MMAD-Purify: A Precision-Optimized Framework for Efficient and Scalable Multi-Modal Attacks

TL;DR

This paper introduces MMAD-Purify, a novel framework that enhances the efficiency and scalability of multi-modal adversarial attacks on diffusion models, achieving high success rates with reduced computational costs and improved robustness.

Contribution

We propose a precision-optimized attack framework using distilled diffusion backbones and noise predictors, significantly improving attack effectiveness and efficiency over existing methods.

Findings

Outperforms existing gradient-based attacks in success rate and efficiency.

Reduces computational costs through a novel noise predictor approach.

Demonstrates high transferability and robustness against defenses.

Abstract

Neural networks have achieved remarkable performance across a wide range of tasks, yet they remain susceptible to adversarial perturbations, which pose significant risks in safety-critical applications. With the rise of multimodality, diffusion models have emerged as powerful tools not only for generative tasks but also for various applications such as image editing, inpainting, and super-resolution. However, these models still lack robustness due to limited research on attacking them to enhance their resilience. Traditional attack techniques, such as gradient-based adversarial attacks and diffusion model-based methods, are hindered by computational inefficiencies and scalability issues due to their iterative nature. To address these challenges, we introduce an innovative framework that leverages the distilled backbone of diffusion models and incorporates a precision-optimized noise predictor to enhance the effectiveness of our attack framework. This approach not only enhances the attack's potency but also significantly reduces computational costs. Our framework provides a cutting-edge solution for multi-modal adversarial attacks, ensuring reduced latency and the generation of high-fidelity adversarial examples with superior success rates. Furthermore, we demonstrate that our framework achieves outstanding transferability and robustness against purification defenses, outperforming existing gradient-based attack models in both effectiveness and efficiency.