MachuPikacchu on Nostr: If you’re a big AI shop pushing open-weight models but not sharing the training ...
If you’re a big AI shop pushing open-weight models but not sharing the training data then you can easily introduce targeted blind spots.
What happens when nation state-backed labs push out state of the art open weight models so that people embed them in their applications with intentional weaknesses?
Reminder: if the service (or model) is free then you’re the “product”. Or in this case you’re the target.
#ai #LLM #cybersecurity
Published at
2024-08-05 17:01:17Event JSON
{
"id": "4b6b2ffd7e7ae2889c51f05947474ca6884cd330b9e387f15e4606908e2fd620",
"pubkey": "1e908fbc1d131c17a87f32069f53f64f45c75f91a2f6d43f8aa6410974da5562",
"created_at": 1722877277,
"kind": 1,
"tags": [
[
"t",
"ai"
],
[
"t",
"LLM"
],
[
"t",
"cybersecurity"
]
],
"content": "If you’re a big AI shop pushing open-weight models but not sharing the training data then you can easily introduce targeted blind spots.\n\nWhat happens when nation state-backed labs push out state of the art open weight models so that people embed them in their applications with intentional weaknesses?\n\nReminder: if the service (or model) is free then you’re the “product”. Or in this case you’re the target.\n\n#ai #LLM #cybersecurity",
"sig": "302829a50718324d1d1dfa3113f607d1fb6831899d1873025a6f8d8184c0960d39505fb88cbe794f030dfd16d330488b3a4959dc0a1a635d5adb8507fa2a7302"
}