Posted inCybersecurity News
Ask a LLM to take you to a company’s login page, and there’s a 1 in 3 chance it will send you to someone else’s website.
A recent study by Netcraft highlights a significant security risk posed by large language models (LLMs) when users ask them for login URLs of well-known brands. In their research, Netcraft found that 34% of the URLs provided by a popular LLM in response to natural language queries about where to log in to 50 major brands were not actually owned or controlled by those brands.