Tech

Hackers now have a terrifying new way to make AI ignore stop signs, cars, and even people

Share
Share


  • RisingAttacK quietly alters key features, tricking AI without changing the image’s appearance
  • Vision systems in self-driving cars could be blinded by nearly invisible image modifications
  • The attack fools top AI models used in cars, cameras, and healthcare diagnostics

Artificial intelligence is becoming more integrated into technologies that rely on visual recognition, from autonomous vehicles to medical imaging – but this increased utility also raises potential security risks, experts have warned.

A new method called RisingAttacK could threaten the reliability of these systems by silently manipulating what AI sees.

Share

Leave a comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Related Articles
Wimbledon has an AI problem, but are tennis players just using technology as a scapegoat?
Tech

Wimbledon has an AI problem, but are tennis players just using technology as a scapegoat?

Wimbledon’s AI-powered line calls have replaced human judges Players like Jack Draper...

Low-cost method can remove CO₂ from air using cold temperatures and common materials
Tech

Low-cost method can remove CO₂ from air using cold temperatures and common materials

Molecular simulation results for structures in the CoRE-MOF-DDEC database. Credit: Energy &...

Low-power, nonvolatile RF switch promises energy-efficient 6G and autonomous vehicle communications
Tech

Low-power, nonvolatile RF switch promises energy-efficient 6G and autonomous vehicle communications

Device schematics and images with material characterization. Credit: Advanced Science (2025). DOI:...

NPU core improves inference performance by over 60%
Tech

NPU core improves inference performance by over 60%

Oaken’s quantization algorithm consisting of three components: (a) threshold-based online-offline hybrid quantization,...