FediThing on Nostr: "Microsoft brainiacs who probed the security of more than 100 of the software giant's ...
"Microsoft brainiacs who probed the security of more than 100 of the software giant's own generative AI products came away with a sobering message: The models amplify existing security risks and create new ones."
"The 26 authors offered the observation that the work of securing AI systems will never be complete."
https://www.theregister.com/2025/01/17/microsoft_ai_redteam_infosec_warning/#AI #Microsoft #LLM #LLMs
Published at
2025-01-19 13:42:21Event JSON
{
"id": "7a579f596ad2c642df2e0012eb1e27655aa0cc13134b189c2521010edb5a8c95",
"pubkey": "16a4446cf6bdbe32ae184b844090b1303e466ef833c583724b455ffd8fabc8c8",
"created_at": 1737294141,
"kind": 1,
"tags": [
[
"t",
"ai"
],
[
"t",
"microsoft"
],
[
"t",
"llm"
],
[
"t",
"LLMs"
],
[
"proxy",
"https://social.chinwag.org/users/FediThing/statuses/113855308854388565",
"activitypub"
]
],
"content": "\"Microsoft brainiacs who probed the security of more than 100 of the software giant's own generative AI products came away with a sobering message: The models amplify existing security risks and create new ones.\"\n\n\"The 26 authors offered the observation that the work of securing AI systems will never be complete.\"\n\nhttps://www.theregister.com/2025/01/17/microsoft_ai_redteam_infosec_warning/\n\n#AI #Microsoft #LLM #LLMs",
"sig": "bf115819a7ae6292f65fb83c816552b8e4b4857e8ff7890acd2f935068a6427401a83a2ae51b1a4128a0c9b9311f6f2e9d2dc89ea350213bb885f1ec7ff6f802"
}
