Security researchers have demonstrated a new technique that hides malicious instructions inside images uploaded to multimodal AI systems. The concealed prompts become visible after the AI downscales the image, allowing the model to execute unintended actions such as extracting calendar data. The method exploits common image resampling methods and has been shown to work against several Google AI products. Researchers released an open‑source tool, Anamorpher, to illustrate the risk and recommend tighter input controls and explicit user confirmations to mitigate the threat.
Read more → 
