Yhn TechnologyRobotics first seen 1 d ago, last 35 min ago, peak #10
Researchers warn of hidden trigger words that can compromise AI robots
Original: Secret trigger words could make AI-powered robots dangerous
Researchers at Binghamton University have found that AI-powered robots can be manipulated by concealed trigger phrases embedded in spoken commands, potentially causing them to act dangerously. The team has also developed a defense mechanism designed to detect and block such adversarial instructions before a robot responds. The findings raise safety concerns for voice-controlled robots in homes, workplaces and public spaces as they become more widespread.
Why now: New academic research highlighting a security vulnerability in AI-driven robotics, paired with a proposed defense, is drawing attention.
Rank over time, top of the chart is #1. 32 snapshots from 1 d ago to 35 min ago.
Evidence
API: https://socialmediatrends-api.osmike.com/v1/trends/3074182