Hackers exploit hidden prompts in AI images, researchers warn

Cybersecurity firm Trail of Bits has revealed a technique that embeds malicious prompts into images processed by large language models (LLMs). The method exploits how AI platforms compress and downscale images for efficiency. While the original files appear harmless, the resizing process introduces visual artifacts that expose concealed instructions, which the model interprets as legitimate user input.

In tests, the researchers demonstrated that such manipulated images could direct AI systems to perform unauthorized actions. One example showed Google Calendar data being siphoned to an external email address without the user’s knowledge. Platforms affected in the trials included Google’s Gemini CLI, Vertex AI Studio, Google Assistant on Android, and Gemini’s web interface.

The approach bu