Skip to content
securitytabs

Covered by 2 outlets — first reported by The Hacker News, Oct 27, 08:22 UTC

OpenAI Compaction Flaw Let Researchers Bypass Hidden Reasoning Protections

MentionsOpenAI

Summary

Security firm Xint has shown that a feature in OpenAI's service that shrinks long conversations, called compaction, could be used to copy out a model's hidden reasoning in plain text, according to The Hacker News. The service normally returns that reasoning only as an encrypted item the user cannot read. Infosecurity Magazine reports the flaw in the OpenAI API was fixed and the researchers received a $6000 bug bounty reward.

AI summary by the SecurityTabs newsroom, checked against The Hacker News, Infosecurity Magazine. Read the outlets below for the full story.

Continue reading

2 outlets, in the order they reported it.

  1. The Hacker NewsFirst report

    OpenAI Compaction Flaw Let Researchers Bypass Hidden Reasoning Protections

    OpenAI's compaction feature, which shrinks a long conversation to save space, could be turned into a way to copy a model's hidden reasoning out in plain text, security firm Xint has shown.

    Read at The Hacker News Details

  2. Infosecurity Magazine

    OpenAI Compaction Flaw Exposed AI Reasoning to Researchers

    Researchers uncovered an OpenAI API flaw that exposed hidden AI reasoning traces, prompting a fix and a $6000 bug bounty reward

    Read at Infosecurity Magazine Details