TTS-generated poisoned audio implants backdoors in SER models achieving high attack success at low poisoning ratios while preserving clean performance.
An overview of the icassp special session on ai security and privacy in speech and audio processing,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Backdoor Attacks on Speech Emotion Recognition via TTS-Generated Poisoning
TTS-generated poisoned audio implants backdoors in SER models achieving high attack success at low poisoning ratios while preserving clean performance.