TooBad: Backdoor Diffusion Models with Ultra-Low Poison Rate and Imperceptible Trigger
This work reveals a critical vulnerability in diffusion models by enabling highly efficient and stealthy backdoor attacks, posing a threat to the security of generative AI systems.
TooBad introduces a trigger optimization technique for backdoor attacks on diffusion models, achieving over 85% attack success rate at only 0.5% poison rate on CIFAR-10, and nearly 100% at 5% poison rate within 3-5 epochs, while evading state-of-the-art defenses.
Diffusion models (DMs), despite their impressive capabilities across a wide range of generative tasks, have been shown to be vulnerable to backdoor attacks. However, existing backdoor methods face critical trade-offs among key factors: attack performance, stealthiness, time complexity, and required poison rates. For example, achieving high attack performance typically demands a high poison rate and prolonged training, which undermines stealthiness, making the attack more detectable by backdoor defenses. This paper proposes TooBad (trigger optimization for backdoor diffusion models), a backdoor framework which introduces a novel DM-tailored trigger optimization technique to dramatically enhance the performance of backdoor attacks on DMs. Experiments on representative benchmarks such as CIFAR-10 show that TooBad can achieve high ASRs ($> 85$%) at only 0.5% poison rate, significantly lower than the 10% typically required by prior work on the same datasets. At 5% poison rate, TooBad reaches nearly 100% ASR within just 3-5 backdoor injection epochs, whereas existing methods need at least 30-50 epochs at double the poison rate for comparable results. Despite its potency, TooBad easily evades SOTA defenses and maintains high utility. These results reveal a critical threat on DMs and highlight the need for more robust defenses against such stealthy yet efficient attacks.