arXiv Artificial Intelligence

Backdoor Attacks on Speech Emotion Recognition via TTS-Generated Poisoning

7 days ago 03.09.2026 07:00 👁 1 views
Backdoor Attacks on Speech Emotion Recognition via TTS-Generated Poisoning

Quick summary

arXiv:2606.21052v2 Announce Type: replace-cross Abstract: Speech Emotion Recognition (SER) systems increasingly leverage self-supervised acoustic representations, yet their vulnerability to training-time attacks remains largely underexplored. This paper presents the first systematic study of poisoning-based backdoor attacks on SER, with a focus on threats enabled by text-to-speech (TTS) generated audio. We introduce a stealthy, low-energy acoustic trigger that can be embedded imperceptibly into both natural and synthetic speech, enabling scalable and consistent poisoning. Our experiments demon

Key takeaways

  • arXiv:2606.21052v2 Announce Type: replace-cross Abstract: Speech Emotion Recognition (SER) systems increasingly leverage self-supervised acoustic representations, yet their vulnerability to training-time attacks remains largely underexplored.
  • This paper presents the first systematic study of poisoning-based backdoor attacks on SER, with a focus on threats enabled by text-to-speech (TTS) generated audio.
  • We introduce a stealthy, low-energy acoustic trigger that can be embedded imperceptibly into both natural and synthetic speech, enabling scalable and consistent poisoning.

Why it matters

“Backdoor Attacks on Speech Emotion Recognition via TTS-Generated Poisoning” shows why AI risk cannot be reduced to answer accuracy. Access controls, logging, human approval and incident response need to be designed into the workflow from the start.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗