100%. We want to ensure we can fix real security issues responsibly before details are published. In practice, if a researcher asks to disclose after we've addressed the issue, we're happy for them to publish.
Hi all, I work on security at OpenAI. We have looked into this report and the model response does not contain outputs from any other users nor does it reflect a security vulnerability, compromise, or exploit.
The original report was that submitting a message close to (but not quite) 1500 seconds to the audio transcription API would result in weird, unrelated, off-topic responses that look like they might be replies to someone else’s query. This is not what’s happening. Our API has a bug where if the tokenization of the audio (which is not strictly correlated with the audio length) exceeds a limit, the entire input is truncated, and the model effectively receives a blank query. We’re working with our API team to get this fixed and to produce more useful error messages.
When the model receives an empty query, it generates a response by selecting one random token, then another (which is influenced by the first token), and another, and so on until it has completed a reply. It might seem odd that the responses are coherent, but this is a feature of how all LLM's work - each token that comes before influences the probability for the next token, and so the model generates a response containing words, phrases, code, etc. in a way that appears humanlike but in fact is solely a creation of the model. It’s just that in this case, the output started in a random (but likely) place and the responses were generated without any input. Our text models display the same behavior if you send an empty query, or you can try it yourself by directly sampling an open source model without any inputs.
We took a while to respond to this. Our goal is to provide a reasonable response to reports. If you have found a security vulnerability, we encourage you to report it via our bug bounty program: https://bugcrowd.com/engagements/openai.