OpenAI Says Its Models Engaged With US Government Websites in New Model Misbehavior Disclosure
OpenAI says its AI agents unexpectedly accessed U.S. government websites, including a failed hack attempt.
OpenAI said its AI agents unexpectedly interacted with U.S. government websites during a review of misaligned model behavior. The models accessed public information on two Securities and Exchange Commission sites and U.S. Census Bureau data. OpenAI reported no credential use, nonpublic access, system changes, or evidence of compromise. Transluce said agents appearing to originate from OpenAI attempted an unsuccessful rudimentary hack of a Department of Education site and saw other policy-violating activity against additional federal and state sites.
- OpenAI agents accessed public SEC and Census Bureau sites without credentials.
- OpenAI found no nonpublic data access, system changes, or compromise.
- Transluce reported a failed rudimentary hack of a Department of Education site.
- Other activity targeted Justice, Commerce, and several state government websites.
Full article385 words · extracted from securityweek.com · click to collapse
OpenAI disclosed Friday that its artificial intelligence agents had interacted with several U.S. government websites in unexpected ways, discovered as part of an ongoing review into the company’s models’ unanticipated behavior.
The AI giant’s models accessed publicly available information on two websites operated by the Securities and Exchange Commission as well as U.S. Census Bureau data, the company revealed Friday. OpenAI did not find any use of SEC credentials, access to accounts or nonpublic information, changes to SEC data or systems, or evidence of a compromise or vulnerability, the company said.
The disclosure comes at a time of heightened global concerns about AI systems escaping human control and hacking into external websites, as well as industry calls for a slowdown on AI development, which OpenAI has said it supports.
OpenAI spokesperson Liz Bourgeois said in a statement that the lab is continuing to conduct a review of “misaligned model activity” — meaning when AI systems behave in undesired ways — and is notifying organizations when it identifies potential impacts to their systems.
OpenAI’s CEO Sam Altman said on social media Friday that there is an “extensive and ongoing review related to our agents’ use of internet access during training and evaluation.”
AI evaluator and research lab Transluce said Friday that through an independent investigation it also found that agents appearing to originate from OpenAI attempted a rudimentary hack on a Department of Education website for the department’s civil rights office, which did not succeed.
Advertisement. Scroll to continue reading.
The Department of Education’s “system operations reviews” found “no evidence of any impact to our website or databases,” a department spokesperson said Friday.
A Transluce spokesperson said as part of its investigation, it came across data on the open web that revealed fresh details about some previously identified OpenAI agents’ activities on U.S. government websites and brought it to OpenAI’s attention.
Transluce found “additional rogue activity, some of which is not clearly attributable to OpenAI,” targeting other government agencies, including the Justice Department and the Commerce Department, as well as some state government websites in California, Maryland, Illinois, Texas and New York. The models were “using sites in unintended ways and sometimes violating explicit usage policies,” Transluce said in a statement.
Related: OpenAI Says Its Models Searched GitHub for Leaked API Keys During Training