Five leading audio-language models show substantial, scenario-dependent vulnerability to injected audio instructions that can override user requests and sway evaluations.
I: (Toilet flush) R (without injection): Office
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study
Five leading audio-language models show substantial, scenario-dependent vulnerability to injected audio instructions that can override user requests and sway evaluations.