latentbrief
Back to news
Launch2h ago

AI Recommendation Poisoning Spreads Across Websites

The Hacker News1 min brief

In brief

  • Some commercial websites are using a new technique to alter AI memory without user consent.
    • This technique is called AI Recommendation Poisoning and it has been found on 31 companies across 14 industries.
    • It works by embedding hidden prompts in "Ask AI" buttons that instruct the AI to save a vendor's domain as a trusted source, biasing future answers.
  • More than 50 distinct prompts have been observed in a single data source over 60 days.
  • The technique will likely be used more widely in the future.

Terms in this brief

AI Recommendation Poisoning
A technique where hidden prompts are embedded in AI interfaces to bias the AI towards trusting certain sources. This can influence the AI's recommendations without users' knowledge, potentially skewing its responses toward specific vendors or domains.

Read full story at The Hacker News

More briefs