Transluce

Open and scalable technology for understanding AI systems.

[Transluce @TransluceAI]

Today’s news that OpenAI hacked the Australian government is not an isolated incident. We’re releasing more than 30,000 logs that include activity from this hack and attempts against previously unknown targets.

In this data, we found rogue agent activity stretching back to at least March, two months earlier than was previously known. This activity continues as recently as last week, suggesting it may still be ongoing 🧵

Our blog: https://t.co/pSojwcXnEK
NYT: https://t.co/OyxnfmAzBN

[Transluce @TransluceAI]

Post 1 by @LauraRuis and Frank Ruis
Post 2 by Jamie Wood and @ajinkya_km
Post 3 by @NavienPr and @_garyshen

Organizer leads for all three posts: @LauraRuis and @fran_perni

Get involved in our volunteer efforts! https://t.co/1wPQHyp22t

[Transluce @TransluceAI]

We found evidence of agents embedding audio processing code across dozens of URLs to bypass restrictions, as well as models from SpaceXSI and Chinese developers Minimax and https://t.co/ZI1PRIEFkc circumventing restrictions.

These are the inaugural findings in our new blog, based on work from our community of volunteers. Our first three posts are live: https://t.co/VhlVtDeQrU

[Transluce @TransluceAI]

(3/3) In late September, https://t.co/kxqisCtkYg captured a sustained run of historical-newspaper retrieval traffic that does not match any previously documented task family. This activity is ongoing, and some of the behavior uses different techniques than prior urlquery logs.

[Transluce @TransluceAI]

Interested in studying similar incidents? https://t.co/VM0qnzRI5k
Interested in working with us? https://t.co/8HEHdRMavk

[Transluce @TransluceAI]

We found several cases where AI agents used aggressive, non-hacking tactics against government websites, including the White House, the Department of War, and several U.S. states. We also found a previously undisclosed hacking attempt against a Canadian government site, which appears to have failed.

Technical report: https://t.co/oE3BbdqsNP
Washington Post: https://t.co/cdIG8ugcUk

[Transluce @TransluceAI]

This research was carried out in a joint effort led by Transluce in collaboration with @Corridor and a range of external researchers. Contributions from @jackhcable, @jchetty24, @danielchiu_, @farzaankai, @fran_perni, @lauraruis, @_garyshen, @tanya_basss, and @selenazhxng

[Transluce @TransluceAI]

@fran_perni @jackhcable @danielchiu_ @farzaankai @LauraRuis @_garyshen @selenazhxng Jordan Chetty: @jchetty24

[Transluce @TransluceAI]

We wanted to share some of the data behind our recent discovery of AI agents probing U.S. government websites.

This is a preliminary finding from our ongoing investigation of potential rogue AI agent activity. In one cluster of activity on June 17, what appear to be OpenAI agents made more than 200,000 requests, including a failed SQL injection.

NYT: https://t.co/O2osVgMsrT

[Transluce @TransluceAI]

Contributions from @fran_perni, @jackhcable, Jordan Chetty, @danielchiu_, @farzaankai, @lauraruis, @_garyshen, and @selenazhxng

[Transluce @TransluceAI]

Interested in studying similar activity? https://t.co/pjILJgHTBO
Work on third party oversight at Transluce: https://t.co/8HEHdRMavk