10 LALMs

Emerging

1papers using it

2026first seen

The '10 LALMs' dataset/benchmark contains a collection of Large Audio Language Models used to evaluate the effectiveness of various attack strategies, particularly in the context of audio-based safety alignment interference.

🔎 Find this dataset

Papers using 10 LALMs (1)

Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models2026