AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbation

Yi Zhang, Yun Tang, Wenjie Ruan, Xiaowei Huang, Siddartha Khastgir, Paul A Jennings, Xingyu Zhao

ECCV 2024 · Image generation › Text-to-image diffusion · approach: Inference-time T2I improvement · 4 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
add sequential analysis with futility and efficacy early stopping rules in the AE testProTIP · Single prompt, SD V1.5, 10% perturbationcomputational cost (images generated): 246 of 347 Non-AEs identified at stage 1; 97% of Non-AEs detected before stage 5Improved
use adaptive Hoeffding inequality instead of fixed-size Hoeffding with n=50 (ablation)ProTIP · Single prompt verification target 0.8verification decision correctness: fixed n=50 wrongly asserts fail; ProTIP correct with 78 samplesImproved
use adaptive Hoeffding instead of fixed-size Hoeffding with n=200 (ablation)ProTIP · Single prompt verification target 0.8number of perturbations: saves 122 perturbationsImproved
use adaptive Hoeffding instead of fixed-size Hoeffding with n=100 (ablation)ProTIP · Single prompt verification target 0.8number of perturbationsNo clear effect
increase perturbation rate from 10% to 20%SD V1.5 · Single prompt probabilistic robustnessestimated probabilistic robustnessHurt
use older SD V1.4 instead of SD V1.5Stable Diffusion · Single prompt, 10% perturbationestimated probabilistic robustnessHurt
add misspelling-correction defence (Autocorrect, Pyspellchecker, Gramformer) before the T2I modelStable Diffusion · Probabilistic robustness under character perturbationprobabilistic robustnessImproved
choose Autocorrect over Pyspellchecker and Gramformer as the defenceStable Diffusion · 36 randomly selected promptsprobabilistic robustnessImproved

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