Back to News
Models
aegis-audio-defense
Kitploit.com·September 26, 2026·1 min read
AI Summary
Defense framework that keeps audio-language models frozen and adds a mid-layer risk gate with late-layer safety adapters to block audio jailbreaks at inference.
From the source
Defense framework that keeps audio-language models frozen and adds a mid-layer risk gate with late-layer safety adapters to block audio jailbreaks at inference.
The full text couldn't be loaded here (the source may require a subscription).
View original at Kitploit.comKeep reading
Was this useful?