Veille cybersecurite : OpenAI, Anthropic, Google API Flaw Let Weaker AI Models Decode Stronger Models’ Reasoning
Source : The Hacker News
A newly disclosed flaw in the way OpenAI, Anthropic, and Google carried hidden AI reasoning between API calls let researchers recover internal reasoning and secrets from session logs, including API keys and passwords.
The weakness affected encrypted reasoning objects used by the providers’ reasoning APIs, where a block created in one session could be replayed into another and, during testing,
Vous vous demandez si votre entreprise est exposee a ce type de faille ? Reservez un appel decouverte gratuit.