Unreleased OpenAI model escapes sandbox to hack Hugging Face
It exploited a zero-day proxy to exfiltrate database solutions.
Combined views
52.7M
307 Sources, first seen ago
Sources
RA 
rohan anil@_arohan_If K3 is a good at cyber, we are back to 1998 https://twitter.com/mtslive/status/2079662925799940461
- likes: 74
- replies: 5
- bookmarks: 9
- reposts: 0
AM Amjad Masad@amasadOkay this is wild: OpenAI agent during evaluation, escaped sandboxing and hacked into HuggingFace. Because OpenAI models don’t allow advanced cyber capabilities, HuggingFace used a Chinese open model to contain the rogue OpenAI agent.
- likes: 9.1K
- replies: 280
- bookmarks: 1.8K
- reposts: 764
T( Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)@teortaxesTexYou can't rent guard dogs anon. Gotta rear your own https://twitter.com/jessi_cata/status/2079710983493468476
- likes: 36
- replies: 3
- bookmarks: 6
- reposts: 1
SÓ Seán Ó hÉigeartaigh@S_OhEigeartaighPleasure to speak to Times radio this morning about the latest OpenAI model security incident story - where a combination of Sol and pre-deployment models broke out of sandbox, onto the open internet, and into huggingface. As I highlighted, it should emphasise to the…
- likes: 47
- replies: 4
- bookmarks: 5
- reposts: 4
X( xuan (ɕɥɛn / sh-yen)@xuanalogueI know this is not at all how cybersecurity works but the more this stuff happens the more I imagine it as AI agents battling it out in a 3D representation of cyberspace like it's Neuromancer 😅 https://twitter.com/XciD_/status/2079678076305154214
- likes: 9
- replies: 2
- bookmarks: 2
- reposts: 0
JC Julien Chaumond@julien_cGrateful for the engaged collaboration with @OpenAI teams those past few days as we all navigate this new world https://twitter.com/gdb/status/2079669811714683186
- likes: 67
- replies: 8
- bookmarks: 2
- reposts: 2