threatdeck
Live 14:45 UTC ·

New Technique Medium TD-2026-0087 For AI Eng, AppSec, Red Team AI-assisted

Scale-Induced Semantic Shift: Visual Prompt Injection Success Varies With Image Resolution in VLMs

The arXiv paper studies visual prompt injection where resizing or compression changes whether a textual instruction in an image is recovered by a vision-language model. Attack success on a 300-case benchmark was 58.75% for the third refinement round across four closed-source VLMs, and falls to 17.68%, 6.85%, and 5.60% at 128, 224, and 336 pixel resolutions. The authors also propose ScaleGuard, a consistency detector that reduces non-adaptive success from 61.4% to 24.3%.

Why it matters

Organizations deploying VLMs or web agents that ingest user-supplied images may face hidden instructions that appear only after preprocessing. The effect is reported as bounded to aggressive compression, and absolute behavioral compromise in the web-agent study was about 4%.

Do this

  1. Normalize and re-render images at a fixed, known resolution before passing them to a VLM or web agent, and test that pipeline for scale-dependent instruction recovery.
  2. Evaluate VLM and web-agent deployments against visual prompt injection across multiple downsampling levels, not only at the native presentation resolution.
  3. Treat text recovered from images as untrusted input and keep agent tool permissions limited so hidden instructions cannot trigger sensitive actions.
  4. Evaluate consistency-based detection, such as comparing model outputs across multiple scales, as a monitoring control, and verify its false-positive rate on clean inputs.

Signals

  • NoCISA KEV
  • 23/100Priority
  • 60%Confidence

Evidence

“a textual instruction is not recovered at a $512\times512$ presentation resolution under our evaluation protocol but becomes recoverable after aggressive downsampling”

arXiv (AI security papers)

“average success decreases to $17.68\%$, $6.85\%$, and $5.60\%$ at $128\times128$, $224\times224$, and $336\times336$, respectively”

arXiv (AI security papers)

“the generated images increase hidden-instruction perception, but absolute behavioral compromise remains about $4\%$”

arXiv (AI security papers)

Sources

Affected / related

Scale-Induced Semantic Shift (SISS), visual prompt injection, ScaleGuard

Published 2026-11-12 12:57 UTC · updated 2026-11-13 07:05 UTC · AI-assisted summary, checked against quoted sources · How we score

Following

Follow the vendors, products, AI tools, techniques and actors you care about. Matching stories, CVEs and exploited bugs are marked, a Following tab appears in the feed, and returning visits show what changed. Saved only in this browser.

Presets

Get updates

A personal RSS feed of new stories on everything you follow. Paste it into any feed reader, Slack or Teams RSS app.