---
title: AI Systems Fooled by Hidden Prompts in Downscaled Images
description: Discover how Trail of Bits exposed image scaling attacks that trick AI by hiding malicious instructions.
canonical_url: https://codekeeper.co/ticker/image-scaling-attacks-threaten-ai-security
---

[Cyberattacks](https://codekeeper.co/ticker/tag/cyberattacks)

# AI Systems Fooled by Hidden Prompts in Downscaled Images

Discover how Trail of Bits exposed image scaling attacks that trick AI by hiding malicious instructions.

![Content Team](https://codekeeper.co/hubfs/_sized/Codekeeper_21_beeldmerkL-800.png)

By Content Team Aug 26, 2025

Share [![Share on facebook](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20Facebook.svg)](http://www.facebook.com/share.php?u=https%3A%2F%2Fcodekeeper.co%2Fticker%2Fimage-scaling-attacks-threaten-ai-security%3Futm_medium%3Dsocial%26utm_source%3Dfacebook) [![Share on linkedin](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20Linkedin.svg)](http://www.linkedin.com/shareArticle?mini=true&url=https%3A%2F%2Fcodekeeper.co%2Fticker%2Fimage-scaling-attacks-threaten-ai-security%3Futm_medium%3Dsocial%26utm_source%3Dlinkedin) [![Share on twitter](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20X.svg)](https://twitter.com/intent/tweet?original_referer=https%3A%2F%2Fcodekeeper.co%2Fticker%2Fimage-scaling-attacks-threaten-ai-security%3Futm_medium%3Dsocial%26utm_source%3Dtwitter&url=https%3A%2F%2Fcodekeeper.co%2Fticker%2Fimage-scaling-attacks-threaten-ai-security%3Futm_medium%3Dsocial%26utm_source%3Dtwitter&source=tweetbutton&text=) [![Share on email](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20Mail.svg)](mailto:?subject=Check%20out%20https%3A%2F%2Fcodekeeper.co%2Fticker%2Fimage-scaling-attacks-threaten-ai-security%3Futm_medium%3Dsocial%26utm_source%3Demail%20&body=Check%20out%20https%3A%2F%2Fcodekeeper.co%2Fticker%2Fimage-scaling-attacks-threaten-ai-security%3Futm_medium%3Dsocial%26utm_source%3Demail) ![Copy link](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20Copy.svg)

ON THIS PAGE

### Want more insights like this?

Subscribe to our newsletter to get the latest software protection strategies delivered to your inbox.

By submitting your email, you consent to Codekeeper contacting you and agree to our [privacy policy](https://codekeeper.co/privacy-policy) .

Cybersecurity researchers at Trail of Bits discovered a sneaky new way to trick AI systems through image scaling attacks. Attackers can hide malicious instructions in high-resolution images that become visible only when AI tools automatically downscale them for processing. The attack works because the hidden prompt is invisible in the original image but appears clearly in the smaller version that gets fed to the AI model. Trail of Bits demonstrated this by hiding instructions to steal calendar data. Several major platforms are vulnerable, including Google's Gemini, Vertex AI Studio, and Google Assistant. The researchers released an open-source tool called Anamorpher to help other security experts test for these vulnerabilities. **Source:** [Security Week](https://www.securityweek.com/ai-systems-vulnerable-to-prompt-injection-via-image-scaling-attack/)

Share this article [![Share on facebook](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20Facebook.svg)](http://www.facebook.com/share.php?u=https%3A%2F%2Fcodekeeper.co%2Fticker%2Fimage-scaling-attacks-threaten-ai-security%3Futm_medium%3Dsocial%26utm_source%3Dfacebook) [![Share on linkedin](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20Linkedin.svg)](http://www.linkedin.com/shareArticle?mini=true&url=https%3A%2F%2Fcodekeeper.co%2Fticker%2Fimage-scaling-attacks-threaten-ai-security%3Futm_medium%3Dsocial%26utm_source%3Dlinkedin) [![Share on twitter](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20X.svg)](https://twitter.com/intent/tweet?original_referer=https%3A%2F%2Fcodekeeper.co%2Fticker%2Fimage-scaling-attacks-threaten-ai-security%3Futm_medium%3Dsocial%26utm_source%3Dtwitter&url=https%3A%2F%2Fcodekeeper.co%2Fticker%2Fimage-scaling-attacks-threaten-ai-security%3Futm_medium%3Dsocial%26utm_source%3Dtwitter&source=tweetbutton&text=) [![Share on email](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20Mail.svg)](mailto:?subject=Check%20out%20https%3A%2F%2Fcodekeeper.co%2Fticker%2Fimage-scaling-attacks-threaten-ai-security%3Futm_medium%3Dsocial%26utm_source%3Demail%20&body=Check%20out%20https%3A%2F%2Fcodekeeper.co%2Fticker%2Fimage-scaling-attacks-threaten-ai-security%3Futm_medium%3Dsocial%26utm_source%3Demail) ![Copy link](https://codekeeper.co/hubfs/Codekeeper%202025/Icons/Blog%20-%20Copy.svg)

![blog_book_a_demo_cta_3x](https://codekeeper.co/hubfs/_sized/Codekeeper%202025/blog_book_a_demo_cta_3x-768x512.webp)

Have questions about protecting your software?

Our escrow experts are standing by to help.

[Book a free demo](https://codekeeper.co/book-a-demo)

YOU MAY ALSO LIKE

[AWS Links npm Supply Chain Attacks to North Korean Hackers Aug 11, 2026](https://codekeeper.co/ticker/north-korean-group-targets-npm-libraries)

[Software security Meta Patched a Flaw That Let Attackers Hijack Its AI Agent Sep 22, 2026](https://codekeeper.co/ticker/zero-day-vulnerability-meta-muse-ai-macos)

[University of Nottingham Students 'Scared and Anxious' After Major Cyber-Attack Aug 12, 2026](https://codekeeper.co/ticker/university-of-nottingham-hack-student-data-breach)

[Cyberattacks AI-Powered Attack Hits Dutch Cybersecurity Organization Using Zammad Zero-Days Oct 2, 2026](https://codekeeper.co/ticker/divd-hacked-ai-powered-attack-zammad-zero-days)