# Audio jailbreaks and speech backdoors

Area: [LLM safety and security](https://mlsanity.com/safety/index.md). HTML: https://mlsanity.com/safety/audio-jailbreaks-and-speech-backdoors/

## Key facts

- Audio jailbreaks and speech backdoors: 56 papers on arXiv since 2022 (data through 14 Oct 2026).
- 21 of its 56 mapped papers (38%) cite “AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models” (2024, arXiv 2412.08608).
- 15 of its 56 mapped papers (27%) cite “Voice Jailbreak Attacks Against GPT-4o” (2024, arXiv 2405.19103).
- 3 new papers 24 Sep–14 Oct.

## Most cited here

- [AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models](https://mlsanity.com/paper/2412.08608/) (2024), cited by 21 papers here
- [Voice Jailbreak Attacks Against GPT-4o](https://mlsanity.com/paper/2405.19103/) (2024), cited by 15 papers here
- [Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models](https://mlsanity.com/paper/2410.23861/) (2024), cited by 15 papers here
- [Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models](https://mlsanity.com/paper/2501.13772/) (2025), cited by 12 papers here
- [Multilingual and Multi-Accent Jailbreaking of Audio LLMs](https://mlsanity.com/paper/2504.01094/) (2025), cited by 10 papers here
- [Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models](https://mlsanity.com/paper/2505.15406/) (2025), cited by 9 papers here
- [Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Sound](https://mlsanity.com/paper/2307.08208/) (2023), cited by 8 papers here
- [SpeechGuard: Exploring the Adversarial Robustness of Multimodal Large Language Models](https://mlsanity.com/paper/2405.08317/) (2024), cited by 8 papers here
- [AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models](https://mlsanity.com/paper/2505.14103/) (2025), cited by 8 papers here
- [JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models](https://mlsanity.com/paper/2505.17568/) (2025), cited by 8 papers here

## New (24 Sep–14 Oct)

- [Backdooring Acoustic Foundation Models for Physically Realizable Triggers](https://mlsanity.com/paper/2610.09819/) (2026-10-07)
- [Where Does the Audio Jailbreak Live? A Controlled Frequency-Depth Audit of AdvWave-P on Qwen2-Audio](https://mlsanity.com/paper/2610.07005/) (2026-10-04)
- [AEGIS: Audio Endogenous Guarding via Internal Signals Against Large Audio-Language Model Jailbreaks](https://mlsanity.com/paper/2609.29287/) (2026-09-24)