Researchers uncovered an OpenAI API flaw that exposed hidden AI reasoning traces, prompting a fix and a $6000 bug bounty reward
OpenAI Compaction Flaw Exposed AI Reasoning to Researchers
About this summary. This is a short excerpt from the description that Infosecurity Magazine published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://www.infosecurity-magazine.com/news/openai-compaction-flaw-ai/
Source attribution: headline and facts are from Infosecurity Magazine (infosecurity-magazine.com). Summary method: excerpt of the source description. See our source attribution policy.
Related coverage
All the security risks Anthropic is worried about before its IPO
Anthropic said its AI systems could drastically reshape the software and cybersecurity sectors in the “near term,” while also laying out a litany of cybersecurity and…
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…
Stolen AI Reasoning Could Help China Build Cheaper Rivals
Xint says a flaw in OpenAI’s compaction process let researchers move reasoning traces between models, potentially making it cheaper to distill a rival AI.
The SonarQube Remediation Agent now fixes Hunter Agent findings
In August, SonarQube Hunter Agent became generally available on SonarQube Cloud, giving teams a way to find the security flaws that pattern-based analysis misses. Broken…
OpenAI Pulls Three AI-Generated Math Papers Over Sign Error
TL;DR OpenAI withdrew three of its 722 AI-generated math manuscripts on October 7 after a sign error in a Weil-classes proof collapsed the argument. The flaw cascaded…
OpenAI GPT-6.1 Sol: An evaluation
Compared with GPT-6 Sol, GPT-6.1 Sol writes 39% more code, lifts its pass rate by 2.20 points, and produces fewer findings per line on every measure we track. GPT-6.1…