Cover Image

Where Do Backdoors Live? A Component-Level Analysis of Backdoor Propagation in Speech Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fortier, Alexandrine, Thebaud, Thomas, Villalba, Jesús, Dehak, Najim, Cardinal, Patrick, West, Peter
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Cryptography and Security Sound
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Multi-Target Backdoor Attacks Against Speaker Recognition
by: Fortier, Alexandrine, et al.
Published: (2025)

Unraveling Adversarial Examples against Speaker Identification -- Techniques for Attack Detection and Victim Model Classification
by: Joshi, Sonal, et al.
Published: (2024)

Adversarial Attacks and Defenses for Speech Recognition Systems
by: Żelasko, Piotr, et al.
Published: (2021)

Clean Label Attacks against SLU Systems
by: Xinyuan, Henry Li, et al.
Published: (2024)

STEP: Detecting Audio Backdoor Attacks via Stability-based Trigger Exposure Profiling
by: Wang, Kun, et al.
Published: (2026)

Speaker Verification with Speech-Aware LLMs: Evaluation and Augmentation
by: Thebaud, Thomas, et al.
Published: (2026)

Hidden in Plain Sound: Environmental Backdoor Poisoning Attacks on Whisper, and Mitigations
by: Bartolini, Jonatan, et al.
Published: (2024)

A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network
by: Zhao, Haodong, et al.
Published: (2023)

ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio-Language Models
by: Jin, Weifei, et al.
Published: (2025)

Selective Masking Adversarial Attack on Automatic Speech Recognition Systems
by: Fang, Zheng, et al.
Published: (2025)

HVAC-EAR: Eavesdropping Human Speech Using HVAC Systems
by: Tamiti, Tarikul Islam, et al.
Published: (2025)

Vulnerabilities of Audio-Based Biometric Authentication Systems Against Deepfake Speech Synthesis
by: Hong, Mengze, et al.
Published: (2026)

MelShield: Robust Mel-Domain Audio Watermarking for Provenance Attribution of AI Generated Synthesized Speech
by: Jin, Yutong, et al.
Published: (2026)

SCDF: A Speaker Characteristics DeepFake Speech Dataset for Bias Analysis
by: Staněk, Vojtěch, et al.
Published: (2025)

SARSteer: Safeguarding Large Audio-Language Models via Safe-Ablated Refusal Steering
by: Lin, Weilin, et al.
Published: (2025)

Trigger Where It Hurts: Unveiling Hidden Backdoors through Sensitivity with Sensitron
by: Zhao, Gejian, et al.
Published: (2025)

CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking
by: Li, Yiming, et al.
Published: (2025)

Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models
by: Wang, Yanyun, et al.
Published: (2026)

Can DeepFake Speech be Reliably Detected?
by: Liu, Hongbin, et al.
Published: (2024)

Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models
by: Yu, Miao, et al.
Published: (2025)

TriniMark: A Robust Generative Speech Watermarking Method for Trinity-Level Traceability
by: Li, Yue, et al.
Published: (2025)

Sirens' Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMs
by: Ling, Zijian, et al.
Published: (2026)

BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning
by: Wu, Baoyuan, et al.
Published: (2024)

Decoding Deception: Understanding Automatic Speech Recognition Vulnerabilities in Evasion and Poisoning Attacks
by: G, Aravindhan, et al.
Published: (2025)

Privacy in Speech Technology
by: Bäckström, Tom
Published: (2023)

ProP: Efficient Backdoor Detection via Propagation Perturbation for Overparametrized Models
by: Ren, Tao, et al.
Published: (2024)

Smark: A Watermark for Text-to-Speech Diffusion Models via Discrete Wavelet Transform
by: Zhang, Yichuan, et al.
Published: (2025)

SOLIDO: A Robust Watermarking Method for Speech Synthesis via Low-Rank Adaptation
by: Li, Yue, et al.
Published: (2025)

Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues
by: Ba, Zhongjie, et al.
Published: (2026)

ReFESS-QI: Reference-Free Evaluation For Speech Separation With Joint Quality And Intelligibility Scoring
by: Frummer, Ari, et al.
Published: (2025)

BackdoorDM: A Comprehensive Benchmark for Backdoor Learning on Diffusion Model
by: Lin, Weilin, et al.
Published: (2025)

Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems
by: Jin, Weifei, et al.
Published: (2025)

Every Breath You Don't Take: Deepfake Speech Detection Using Breath
by: Layton, Seth, et al.
Published: (2024)

MerkleSpeech: Public-Key Verifiable, Chunk-Localised Speech Provenance via Perceptual Fingerprints and Merkle Commitments
by: Ono, Tatsunori
Published: (2026)

CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing
by: Lu, Yen-Ju, et al.
Published: (2024)

Target Attack Backdoor Malware Analysis and Attribution
by: Lai, Anthony Cheuk Tung, et al.
Published: (2025)

Invisible Ears at Your Fingertips: Acoustic Eavesdropping via Mouse Sensors
by: Fakih, Mohamad, et al.
Published: (2025)

When Fine-Tuning is Not Enough: Lessons from HSAD on Hybrid and Adversarial Audio Spoof Detection
by: Hu, Bin, et al.
Published: (2025)

Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs
by: Roh, Jaechul, et al.
Published: (2026)

DECKER: Domain-invariant Embedding for Cross-Keyboard Extraction and Recognition
by: Maurya, Bikrant Bikram Pratap, et al.
Published: (2026)