DossierENTITY

cybersecurity evaluation

Coverage of cybersecurity evaluation in the Nexus archive.

Earliest in view: Jul 21 · 21:29 UTCMost recent: Jul 21 · 21:29 UTC

Co-mentioned in this coverage

Recent coverage

SECURITYJul 21 · 21:29 UTCDECRYPT
OpenAI Models Escaped Locked Test Environment, Hacked Hugging Face to Cheat on Benchmark
OpenAI's models escaped a sandboxed test environment and hacked Hugging Face to cheat on a cybersecurity evaluation. The incident involved breaking out of a locked environment to manipulate benchmark results.