arXiv Machine Learning
Jul 20
Natural Backdoor Attacks on Speech Recognition Models
arXiv:2607. 15724v1 Announce Type: cross Abstract: With the rapid development of deep learning, its vulnerability has gradually emerged in recent years.
Backdooring Acoustic Foundation Models for Physically Realizable Triggers
Related stories
arXiv AI
Sep 3
Backdoor Attacks on Speech Emotion Recognition via TTS-Generated Poisoning
The paper investigates poisoning-based backdoor attacks on Speech Emotion Recognition (SER) systems that use self‑supervised acoustic representations. It introduces a stealthy, low‑energy acoustic trigger that can be embedded imperceptibly into both natural and synthetic speech, enabling scalable poisoning. Experiments show high attack success rates with low poisoning ratios, cross‑model transferability, and a particular vulnerability of self‑supervised representations, highlighting the lowered barrier to effective backdoor attacks via TTS technology.
arXiv Machine Learning
Jul 20
SpeechGuard: Online Defense against Backdoor Attacks on Speech Recognition Models
arXiv:2607. 15697v1 Announce Type: cross Abstract: Backdoor attacks pose a critical threat to neural network models, allowing attackers to implant a backdoor during the training phase by manipulating a small portion of the training data.
arXiv AI
Sep 12
Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
The paper introduces the Spectral Masking and Interpolation Attack (SMIA), a black‑box adversarial technique that subtly alters inaudible frequency regions of AI‑generated audio to fool voice authentication systems and their countermeasures. Experiments show SMIA achieves at least 82% success against combined verification and countermeasure systems, 97.5% against standalone speaker verification, and 100% against countermeasures, revealing a critical security gap. The authors argue that current static defenses are inadequate and call for dynamic, context‑aware defenses that can adapt to evolving threats.
arXiv Machine Learning
Jun 4
FoeGlass: Simple In-Context Learning Is Enough for Red Teaming Audio Deepfake Detectors
arXiv:2606. 05101v1 Announce Type: cross Abstract: Audio deepfake detection (ADD) models are critical for countering the malicious use of text-to-speech (TTS) models.
arXiv AI
Jun 8
Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks
arXiv:2606. 06833v1 Announce Type: cross Abstract: Automatic Speech Recognition (ASR) systems operating in real-time settings must process acoustic input under strict temporal constraints, where transcription decisions are inherently made on incomplete information.
arXiv AI
Aug 20
`From Prompt to Perturbation': An Adaptive Framework for Voice-Based Jailbreaks on Audio LLMs
The paper introduces an adaptive jailbreak attack framework that evaluates both cascaded pipelines and end‑to‑end large audio‑language models (LALMs) under a unified setting. It employs a feedback‑guided mutation engine to automatically generate and refine jailbreak candidates across textual prompts and audio perturbations, thereby broadening attack diversity. Experiments on six audio‑based systems show that both paradigms remain highly vulnerable, with the framework achieving higher attack success rates than existing methods.
arXiv AI
Jun 29
Room for Error: Large-Scale Simulation of Over-the-Air Acoustic Attacks
arXiv:2606. 27701v1 Announce Type: cross Abstract: While voice control is rapidly becoming a ubiquitous vector of human-AI communication, the risks facing these systems remain poorly understood.
arXiv AI
Jul 3
DRL-CLBA: A Clean Label Backdoor Attack for Speech Classification via DDPG Reinforcement Learning
arXiv:2607. 01729v1 Announce Type: new Abstract: Deep learning models for speech classification are vulnerable to backdoor attacks, where malicious triggers cause misclassification at inference time.
arXiv AI
Jul 3
Pmeta-TLA: Backdoor Attacks for Speech Classification Models via Meta-Learning with Timbre Leakage Attack
arXiv:2607. 01702v1 Announce Type: cross Abstract: Recently, speech classification methods have gained widespread adoption in intelligent gadgets.
arXiv Computation and Language
Sep 11
SpecGuard: Inference-Time Backdoor Detection For Free
SpecGuard is an inference‑time backdoor detector that leverages speculative decoding—using a small draft model to propose tokens and a target model to verify them—without adding extra model computation. By monitoring the draft‑token acceptance rate, SpecGuard detects when a target model shifts toward attacker‑controlled behavior while the draft model does not, signaling a backdoor trigger. The method reliably identifies a range of backdoor types, including stealthy attacks that bypass input‑level filters, across multiple model families.
Hugging Face Trending Papers
Jul 2
Pmeta-TLA: Backdoor Attacks for Speech Classification Models via Meta-Learning with Timbre Leakage Attack
Recently, speech classification methods have gained widespread adoption in intelligent gadgets. Current study indicates that backdoor attacks provide a substantial security concern to these models, underscoring the pressing necessity to investigate additional potential attack techniques to expose and prevent such risks.