OpenAI Says Attack Notifications Will Take Months as Report Publishes 180K Payloads
dylfreed · x · 2026-09-26
A newly published security report on the OpenAI–Hugging Face attack includes an evidence viewer and a downloadable dataset of over 180,000 payloads and recovered texts — the most comprehensive public data on the incident to date.
OpenAI said it had not had a chance to review the report, but that the activity was consistent with current investigations. Given the number of cases and verification needs, it expects the work and notifications to affected third parties to take months.
More from Safety
- UC Berkeley's SubWM watermark detects LLM distillation even after laundering attacks — sumanthd17 · 2026-11-11
- Microsoft patent reveals real-time AI speech rewriting with lip-synced live video — Significant_Mail5398 · 2026-11-11
- Microsoft Research: editing under 10 neurons turns an agent into a sleeper backdoor — DimitrisPapail · 2026-11-11
- Safety community's best spend: a 2-year institution teaching LLM internals — viemccoy · 2026-11-11
- The same people cite an existential AI race with China and want looser GPU export controls — austinc3301 · 2026-11-11
- Redwood reframed: doing narrow safety work to buy odds, not solve AI safety broadly — austinc3301 · 2026-11-11