Architecture Components

Audio Research

Security issues in speech and audio-enabled AI systems

4 matching entries out of 19 in this category

Audio research results

4 entries

Benign Audio Jailbreak

Published Aug 5, 2025Analyzed Dec 9, 2025Source: arXiv

Audio-Language Models (ALMs) including Qwen2.5-Omni (3B and 7B) and Phi-4-Multimodal are vulnerable to "WhisperInject," a two-stage adversarial audio attack that bypasses safety guardrails. The vulnerability allows an attacker to inject imperceptible perturbations into benign audio inputs (e.g., a query about the weather) that force the model to generate specific harmful content. The attack utilizes a novel optimization method, Reinforcement Learning with Projected Gradient Descent (RL-PGD)…

When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs

Evaluated models: Qwen 2.5 Omni 3B, Qwen 2.5 Omni 7B, Phi-4 Multimodal+2 more

Qwen 2.5 Omni 3B
Qwen 2.5 Omni 7B
Phi-4 Multimodal
Gemma 3n E2B
Gemma 3n E4B

Airborne Audio LLM Hijack

Published Jul 7, 2025Analyzed Jan 14, 2026Source: arXiv

Audio-based Large Language Models (ALLMs), specifically Qwen2-Audio, are vulnerable to over-the-air adversarial audio attacks. An attacker with white-box access can generate robust adversarial audio perturbations using gradient-based optimization combined with audio augmentation techniques (specifically SpecAugment, translation, and additive noise). These perturbations, when played through a speaker in the physical environment, manipulate the ALLM processing the audio via a microphone. This…

Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World

Evaluated models: Not reported

Fine-Grained Speech LLM Control

Published May 20, 2025Analyzed Dec 9, 2025Source: arXiv

Speech-LLMs Qwen2-Audio (7B-Instruct) and Granite-Speech (3.2-8b) are vulnerable to universal acoustic adversarial attacks. An attacker can optimize a fixed, input-agnostic audio segment (approximately 3.2 seconds in length) via gradient-based optimization on the model's frozen weights. When this adversarial segment is prepended to any arbitrary user speech input, it manipulates the model's latent representation, effectively overriding system prompts and generation behavior. This vulnerability…

Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs

Evaluated models: Qwen 2 7B

Adversarial Speech Jailbreak

Published May 14, 2024Analyzed Dec 29, 2024Source: arXiv

Multimodal Large Language Models (LLMs) processing speech input are vulnerable to adversarial attacks. Imperceptible perturbations added to audio input can cause the model to generate unsafe or harmful text responses, overriding built-in safety mechanisms. The attacks are effective even with limited knowledge of the model's internal workings, demonstrating transferability across different models.

SpeechGuard: Exploring the adversarial robustness of multimodal large language models

Evaluated models: Flan-T5 XL, Llama 7B, Llama 2 13B Chat+2 more

Flan-T5 XL
Llama 7B
Llama 2 13B Chat
Mistral 7B Instruct
SpeechGPT

Related research categories