Robots that read the world through cameras now lean on large vision-language models to interpret what they see and decide what to do next. These models handle images and text together, so any words that fall inside the camera frame become part of the input. A stop sign, a street name, a sticker on a wall. The overthinking behavior at the center of the attack Researchers at Michigan Technological University have shown that this reading … More →
The post An AI overthinking attack can tie a robot up for over a minute appeared first on Help Net Security.
You must login to view this content
Over the past twelve months, researchers documented intrusions in which AI ran exploitation workflows autonomously, generating thousands of commands across dozens of sessions with minimal human direction, according to Check Point’s AI Security Report 2026. AI-powered cyber attacks The attackers posing the greatest risk are those orchestrating AI across multiple stages of the attack chain without requiring human intervention. They achieve this by obtaining capable AI models and removing their safety controls. Attackers gain AI … More →
The post AI used to help plan the break-in, now it’s doing the break-in appeared first on Help Net Security.
You must login to view this content