AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models

Sheng-Yen Chou, Pin-Yu Chen, Tsung-Yi Ho

NeurIPS 2023 · Image generation › Fast diffusion sampling · approach: Diffusion theory and design space · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
backdoor with VillanDiffusion at 90% poison rate versus clean model (ablation)DDPM with 7 samplers · CIFAR10, Hat triggerFID: about 10\%Hurt
backdoor at poison rate below 70% (ablation)DDPM with 7 samplers · CIFAR10, Hat triggerFID: 70\%Improved
increase poison rate to about 10% (ablation)DDPM backdoor · CIFAR10, Hat triggerMSE to target: about 10\%Improved
backdoor with 20% poison rateDDPM · CelebA-HQFID: 25\% $\sim$ 85\%Hurt
use DDIM sampler randomness eta=1 instead of eta=0 with BadDiffusion (ablation)BadDiffusion · CIFAR10backdoor success (MSE)Mixed
replace BadDiffusion objective with VillanDiffusion on ODE samplers (ablation)backdoor loss · CIFAR10 ODE samplersbackdoor successImproved
apply inference-time clipping range [-1, 1] to all samplers (ablation)backdoored DMs · CIFAR10FID and MSENo clear effect
higher caption similarity between trigger and clean caption (ablation)caption-trigger backdoor on Stable Diffusion · CelebA-HQ-Dialog and Pokemon CaptionMSE and MSE thresholdHurt

Later papers that compared with this method

2 later accepted papers report VillanDiffusion as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy