Poisoning AI Training Data
ID: 7598308b-d54f-5747-bf01-7030678de90f
STIX ID: report--7598308b-d54f-5747-bf01-7030678de90f
Feed Name: Schneier on Security
A blog post describes an experiment where the author created a fake webpage ranking “the best tech journalists at eating hot dogs,” which was then echoed by Google’s Gemini/AI Overviews and ChatGPT within 24 hours (while Claude resisted), highlighting how easily AI systems can be manipulated by fabricated web content and cautioning against over-trusting such outputs.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.