DiffDefense: Defending against Adversarial Attacks via Diffusion Models
This addresses security vulnerabilities in ML systems for applications like image classification, though it is incremental as it builds on existing diffusion methods.
The paper tackles the problem of defending machine learning classifiers against adversarial attacks by using Diffusion Models for input reconstruction, achieving robustness without modifying the classifiers and maintaining clean accuracy and speed.
This paper presents a novel reconstruction method that leverages Diffusion Models to protect machine learning classifiers against adversarial attacks, all without requiring any modifications to the classifiers themselves. The susceptibility of machine learning models to minor input perturbations renders them vulnerable to adversarial attacks. While diffusion-based methods are typically disregarded for adversarial defense due to their slow reverse process, this paper demonstrates that our proposed method offers robustness against adversarial threats while preserving clean accuracy, speed, and plug-and-play compatibility. Code at: https://github.com/HondamunigePrasannaSilva/DiffDefence.