The Economic Times2026-09-26 00:37:32

OpenAI says its models engaged with US government websites in new model misbehavior disclosure

The AI giant's models accessed publicly available information on two websites operated by the Securities and Exchange Commission as well as U.S.

Summary

Census Bureau data, the company revealed Friday.

ai model security concernsopenai ai models misbehavioropenai public data accessai systems escaping controlartificial intelligence unexpected behaviorus government websites hack

This is a brief wire summary — the full story (linked below) has the complete details.

KazaSec's take

AI-related security incidents are a genuinely new category — prompt injection, model manipulation, and data leakage through an LLM integration don't map cleanly onto traditional application security testing, and are worth assessing deliberately rather than assuming existing controls already cover them.

Coverage details

Source: The Economic Times
Published: 2026-09-26 00:37:32
Author: ap
Category: toptechnology

Worried this kind of story could be about you next?

We help organizations find and fix the gaps before they make headlines.

Request a Security Assessment Browse Services