AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Reconstructing Template-Memorized Images from Natural Prompts

Sol Yarkoni, Mahmood Sharif, Roi Livni

ICML 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Vision-language model robustness · 0 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
use short benign collocation prompts instead of training-set captionsextraction attack · SD 1.4number of prompts needed: 350{,}000 -> 108Improved
apply BE-PRSS prompt-variation mitigationSD 1.4 with template collocations · 43 memorizing collocationscollocations still producing template image: 28 -> 22No clear effect
use BE-PRSS detection threshold 1.0 on template memorizationBE-PRSS detector · template-memorized promptsaccuracy: 0.595Hurt
use attack against newer models (SD 3.5)template attack · Stable Diffusion 3.5 Mediumtemplate reconstructionHurt
use collocations from SD 1.4 on real-user prompts (Midjourney)template attack · Midjourney promptsprompts producing template image: 8 out of 20Improved
use collocations from SD 1.4 on real-user prompts (DiffusionDB)template attack · DiffusionDB promptsprompts producing template image: 7 out of 15Improved

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