Cover Image

SPBA: Utilizing Speech Large Language Model for Backdoor Attacks on Speech Classification Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yao, Wenhan, Xiao, Fen, Chen, Xiarun, Liu, Jia, He, YongQiang, Wen, Weiping
Format:	Preprint
Published:	2025
Subjects:	Sound Artificial Intelligence Computation and Language Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

EmoAttack: Utilizing Emotional Voice Conversion for Speech Backdoor Attacks on Deep Speech Classification Models
by: Yao, Wenhan, et al.
Published: (2024)

Pureformer-VC: Non-parallel Voice Conversion with Pure Stylized Transformer Blocks and Triplet Discriminative Training
by: Yao, Wenhan, et al.
Published: (2025)

Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation for Embedding Undetectable Vulnerabilities on Speech Recognition
by: Yao, Wenhan, et al.
Published: (2024)

Pureformer-VC: Non-parallel One-Shot Voice Conversion with Pure Transformer Blocks and Triplet Discriminative Training
by: Yao, Wenhan, et al.
Published: (2024)

DualSpeechLM: Towards Unified Speech Understanding and Generation via Dual Speech Token Modeling with Large Language Models
by: Wang, Yuanyuan, et al.
Published: (2025)

Investigating Neural Audio Codecs for Speech Language Model-Based Speech Generation
by: Li, Jiaqi, et al.
Published: (2024)

Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis
by: Liao, Shijia, et al.
Published: (2024)

SuperCodec: A Neural Speech Codec with Selective Back-Projection Network
by: Zheng, Youqiang, et al.
Published: (2024)

NAST: Noise Aware Speech Tokenization for Speech Language Models
by: Messica, Shoval, et al.
Published: (2024)

Evaluating Text-to-Speech Synthesis from a Large Discrete Token-based Speech Language Model
by: Wang, Siyang, et al.
Published: (2024)

EmoQ: Speech Emotion Recognition via Speech-Aware Q-Former and Large Language Model
by: Yang, Yiqing, et al.
Published: (2025)

Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders
by: Shan, Weiqiao, et al.
Published: (2025)

CosyEdit: Unlocking End-to-End Speech Editing Capability from Zero-Shot Text-to-Speech Models
by: Chen, Junyang, et al.
Published: (2026)

Improving Speech Enhancement by Cross- and Sub-band Processing with State Space Model
by: Li, Jizhen, et al.
Published: (2025)

Zero-Shot Recognition of Dysarthric Speech Using Commercial Automatic Speech Recognition and Multimodal Large Language Models
by: Alsayegh, Ali, et al.
Published: (2025)

MPO: Multidimensional Preference Optimization for Language Model-based Text-to-Speech
by: Xia, Kangxiang, et al.
Published: (2025)

SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models
by: Zhang, Xin, et al.
Published: (2023)

S2ST-Omni: Hierarchical Language-Aware SpeechLLM Adaptation for Multilingual Speech-to-Speech Translation
by: Pan, Yu, et al.
Published: (2025)

A Neural Speech Codec for Noise Robust Speech Coding
by: Huang, Jiayi, et al.
Published: (2023)

Integrating Pause Information with Word Embeddings in Language Models for Alzheimer's Disease Detection from Spontaneous Speech
by: Pu, Yu, et al.
Published: (2025)

Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages
by: Shao, Mingchen, et al.
Published: (2025)

GenSE: Generative Speech Enhancement via Language Models using Hierarchical Modeling
by: Yao, Jixun, et al.
Published: (2025)

SECodec: Structural Entropy-based Compressive Speech Representation Codec for Speech Language Models
by: Wang, Linqin, et al.
Published: (2024)

Streaming Speech Recognition with Decoder-Only Large Language Models and Latency Optimization
by: Wan, Genshun, et al.
Published: (2026)

On Calibration of Speech Classification Models: Insights from Energy-Based Model Investigations
by: Hao, Yaqian, et al.
Published: (2024)

TraceableSpeech: Towards Proactively Traceable Text-to-Speech with Watermarking
by: Zhou, Junzuo, et al.
Published: (2024)

Comprehend and Talk: Text to Speech Synthesis via Dual Language Modeling
by: Cao, Junjie, et al.
Published: (2025)

ToneUnit: A Speech Discretization Approach for Tonal Language Speech Synthesis
by: Tao, Dehua, et al.
Published: (2024)

VoxInstruct: Expressive Human Instruction-to-Speech Generation with Unified Multilingual Codec Language Modelling
by: Zhou, Yixuan, et al.
Published: (2024)

From Human Speech to Ocean Signals: Transferring Speech Large Models for Underwater Acoustic Target Recognition
by: Huang, Mengcheng, et al.
Published: (2026)

Few-Shot and Pseudo-Label Guided Speech Quality Evaluation with Large Language Models
by: Zezario, Ryandhimas E., et al.
Published: (2026)

A Transcription Prompt-based Efficient Audio Large Language Model for Robust Speech Recognition
by: Li, Yangze, et al.
Published: (2024)

Can Large Language Models Aid in Annotating Speech Emotional Data? Uncovering New Frontiers
by: Latif, Siddique, et al.
Published: (2023)

A Study on Zero-shot Non-intrusive Speech Assessment using Large Language Models
by: Zezario, Ryandhimas E., et al.
Published: (2024)

SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation Methods
by: Huang, Wen, et al.
Published: (2025)

Language-Codec: Bridging Discrete Codec Representations and Speech Language Models
by: Ji, Shengpeng, et al.
Published: (2024)

Attention-weighted Centered Kernel Alignment for Knowledge Distillation in Large Audio-Language Models Applied to Speech Emotion Recognition
by: Yang, Qingran, et al.
Published: (2026)

Analysis of Self-Supervised Speech Models on Children's Speech and Infant Vocalizations
by: Li, Jialu, et al.
Published: (2024)

Distinguishing Neural Speech Synthesis Models Through Fingerprints in Speech Waveforms
by: Zhang, Chu Yuan, et al.
Published: (2023)

Speech Denoising with Auditory Models
by: Saddler, Mark R., et al.
Published: (2020)