AI malware can rewrite itself to evade detection

Google's Threat Intelligence Group found experimental malware called PROMPTFLUX that could ask Gemini to rewrite its own code. One version was designed to do that every hour. Why would malware keep rewriting itself? To make it harder to recognize.

Security software can look for known patterns in malicious code. If that code keeps changing, the malware becomes a moving target. That does not automatically make it invisible to current security tools, but it can make some types of detection more difficult.

There is an important reality check here. PROMPTFLUX was still being developed when Google found it. Researchers had yet to see it successfully compromise a victim's device or network, and Google disabled assets connected to the activity.

What caught my attention is what came next. Google has since documented AI being used by malware during live attacks. It has also uncovered an Android backdoor that can use AI to understand what is happening on a phone and help decide what to do next. That tells us where this could be heading. So let's break down how AI-powered malware works and what you can do to protect yourself.

AN AI CYBERATTACK COULD TURN OFF AMERICA'S LIGHTS BEFORE WASHINGTON EVEN UNDERSTANDS WHY

NEW!