Concealed Backdoor Attack on Diffusion Models for Smart Devices with Non-standard Gaussian Distribution Noise

Li, J. and Tan, Y.-A. and Fan, S. and Li, F. and Liu, X. and Liu, R. and Li, Y. and Meng, W. (2024) Concealed Backdoor Attack on Diffusion Models for Smart Devices with Non-standard Gaussian Distribution Noise. IEEE Transactions on Consumer Electronics. ISSN 0098-3063

Text (conceal)
conceal.pdf - Accepted Version
Available under License Creative Commons Attribution.
Download (943kB)

Abstract

Edge AI-driven diffusion models (DMs) are increasingly integrated into consumer devices for high-quality data generation and content creation. This paper introduces InvisibleDiffusion, a novel backdoor attack framework for diffusion models in consumer electronics, designed to remain undetected by utilizing a non-standard Gaussian distribution as a concealed trigger. Unlike previous backdoor methods, InvisibleDiffusion does not rely on obvious visual triggers, enhancing its stealthiness. Extensive experiments demonstrate that InvisibleDiffusion achieves high attack efficacy against DDPM and DDIM models on CIFAR-10 and CelebA datasets, while maintaining the functional integrity of the models. Our code is available for reproducibility at https://anonymous.4open.science/r/b2hoaWNhbnRzZWV0aGF0bm9vb29vb29vb29v.