Skip to content
LowResearchPeer-reviewed

Exploring Security Vulnerabilities in Multilingual Speech Translation Systems via Deceptive Inputs

Published
Record updated
View JSON

Summary

Researchers show that speech translation systems can be compromised with imperceptible audio manipulations. They adapt perturbation-based attacks from automatic speech recognition to speech translation, and propose a music generation method that steers translations toward targeted outputs. Adversarial music achieved this more covertly, and the attacks worked across multiple languages and translation models.