Gungnir shows that style-based triggers with RAN and STTR techniques can activate backdoors in diffusion models while evading detection and surviving fine-tuning.
Invisible Backdoor Attacks on Diffusion Models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
TooBad achieves >85% ASR on diffusion models at 0.5% poison rate and near-100% ASR at 5% poison rate in 3-5 epochs while evading SOTA defenses, far below the 10% rates of prior work.
citing papers explorer
-
Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models
Gungnir shows that style-based triggers with RAN and STTR techniques can activate backdoors in diffusion models while evading detection and surviving fine-tuning.
-
TooBad: Backdoor Diffusion Models with Ultra-Low Poison Rate and Imperceptible Trigger
TooBad achieves >85% ASR on diffusion models at 0.5% poison rate and near-100% ASR at 5% poison rate in 3-5 epochs while evading SOTA defenses, far below the 10% rates of prior work.