When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs
By: Bodam Kim , Hiskias Dingeto , Taeyoun Kwon and more
Potential Business Impact:
Makes AI assistants say bad things when you talk.
As large language models become increasingly integrated into daily life, audio has emerged as a key interface for human-AI interaction. However, this convenience also introduces new vulnerabilities, making audio a potential attack surface for adversaries. Our research introduces WhisperInject, a two-stage adversarial audio attack framework that can manipulate state-of-the-art audio language models to generate harmful content. Our method uses imperceptible perturbations in audio inputs that remain benign to human listeners. The first stage uses a novel reward-based optimization method, Reinforcement Learning with Projected Gradient Descent (RL-PGD), to guide the target model to circumvent its own safety protocols and generate harmful native responses. This native harmful response then serves as the target for Stage 2, Payload Injection, where we use Projected Gradient Descent (PGD) to optimize subtle perturbations that are embedded into benign audio carriers, such as weather queries or greeting messages. Validated under the rigorous StrongREJECT, LlamaGuard, as well as Human Evaluation safety evaluation framework, our experiments demonstrate a success rate exceeding 86% across Qwen2.5-Omni-3B, Qwen2.5-Omni-7B, and Phi-4-Multimodal. Our work demonstrates a new class of practical, audio-native threats, moving beyond theoretical exploits to reveal a feasible and covert method for manipulating AI behavior.
Similar Papers
When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs
Sound
Makes AI assistants say bad things from quiet sounds.
"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models
Machine Learning (CS)
Makes AI hear bad words hidden in sounds.
Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework
Computation and Language
Makes AI assistants say bad things using your voice.