Jonas Geiping reviews the reasoning extraction attack: vendors find patching difficult, and the Astra attack continued through this week
Jonas Geiping reviewed the aftermath of the previously disclosed reasoning extraction attack: reasoning from all frontier vendors can be extracted, and vendors find it very hard to fully patch, with the attack against Astra continuing through this week. He mentioned that he has compiled the update into a report and pointed to OpenAI's recent report on disrupting coordinated model distillation activity. The quoted content shows that two months after the reasoning extraction attack was published, the authors audited the mitigations introduced since then and found that reasoning could still be extracted from Astra/Sol-6.1 via third-party API providers, and they have disclosed this to OpenAI and Anthropic.
After our initial disclosure that reasoning from all frontier providers could be extracted, what happened?
For one, it turned out to be quite difficult for providers to patch this thoroughly, allowing us to keep attacks working on Astra until this week...
We've collected our updates in a report linked below and your can also find more info in OpenAIs recent report.
Two months after our reasoning extraction attack release, we audited mitigations introduced since then and found that we still can extract reasoning from Astra/Sol-6.1 via third-party API providers.
We disclosed our findings to OpenAI and Anthropic...
https://openai.com/index/disrupting-a-coordinated-model-distillation-campaign/View the quoted post on X