TrojFlow fine-tunes a rectified-flow generator so specific trigger-noise inputs produce attacker-chosen images, keeps benign outputs usable, and qualitatively evades UFID and TERD defenses on CIFAR-10 and CelebA.
Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Diffusion models (DM) have become state-of-the-art generative models because of their capability to generate high-quality images from noises without adversarial training. However, they are vulnerable to backdoor attacks as reported by recent studies. When a data input (e.g., some Gaussian noise) is stamped with a trigger (e.g., a white patch), the backdoored model always generates the target image (e.g., an improper photo). However, effective defense strategies to mitigate backdoors from DMs are underexplored. To bridge this gap, we propose the first backdoor detection and removal framework for DMs. We evaluate our framework Elijah on hundreds of DMs of 3 types including DDPM, NCSN and LDM, with 13 samplers against 3 existing backdoor attacks. Extensive experiments show that our approach can have close to 100% detection accuracy and reduce the backdoor effects to close to zero without significantly sacrificing the model utility.
citation-role summary
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
TrojFlow: Flow Models are Natural Targets for Trojan Attacks
TrojFlow fine-tunes a rectified-flow generator so specific trigger-noise inputs produce attacker-chosen images, keeps benign outputs usable, and qualitatively evades UFID and TERD defenses on CIFAR-10 and CelebA.