Backdoor Attacks on Speech Emotion Recognition via TTS-Generated Poisoning

arXiv:2606.21052 · cs.SD, cs.AI, cs.CR · Submitted 2026-06-19 · Read on arXiv

cs.SD, cs.AI, cs.CR

Submitted: 2026-06-19

Updated: 2026-09-01

Terminology

• Accuracy — 21× in this paper · explained in 1 episode
• Robustness — 11× in this paper · explained in 5 episodes
• Speech Emotion Recognition — 11× in this paper
• Attack Success Rate — 9× in this paper
• Attack Success Rate (ASR) — 4× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Transferability — 3× in this paper · explained in 4 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Adversarial Attacks — 2× in this paper · explained in 1 episode
• Affective Computing — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Self-Supervised Learning — 2× in this paper · explained in 8 episodes
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Adversarial Training — 1× in this paper · explained in 1 episode
• Distillation — 1× in this paper · explained in 2 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes

Sources

• wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
• data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language
• Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
• Where Do Backdoors Live? A Component-Level Analysis of Backdoor Propagation in Speech Language Models
• Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Sound
• Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation for Embedding Undetectable Vulnerabilities on Speech Recognition
• EmoBack: Backdoor Attacks Against Speaker Identification Using Emotional Prosody
• UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training

Related papers

• Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
• Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
• AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
• SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
• WASIL: In-the-Wild Arabic Spoken Interactions with LLMs
• Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment