# Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Models

arXiv: https://arxiv.org/abs/2506.11521 · HTML: https://mlsanity.com/paper/2506.11521/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 66 of its 134 references that are in the map.
- First posted on arXiv 13 Jun 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)
- LLM safety and security / [Vision-language and text-to-image safety](https://mlsanity.com/safety/vision-language-and-text-to-image-safety/)

## Builds on (most cited first, 30 of 66)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [Audio Adversarial Examples: Targeted Attacks on Speech-to-Text](https://mlsanity.com/paper/1801.01944/) (2018)
- [LLaMA-Omni: Seamless Speech Interaction with Large Language Models](https://mlsanity.com/paper/2409.06666/) (2024)
- [A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models](https://mlsanity.com/paper/2402.13457/) (2024)
- [JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs](https://mlsanity.com/paper/2402.05668/) (2024)
- [Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models](https://mlsanity.com/paper/2305.01219/) (2023)
- [Best-of-N Jailbreaking](https://mlsanity.com/paper/2412.03556/) (2024)
- [T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models](https://mlsanity.com/paper/2407.05965/) (2024)
- [Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning](https://mlsanity.com/paper/2401.05949/) (2024)
- [Automatic Speech Recognition using Advanced Deep Learning Approaches: A survey](https://mlsanity.com/paper/2403.01255/) (2024)
- [Can You Hear It? Backdoor Attacks via Ultrasonic Triggers](https://mlsanity.com/paper/2107.14569/) (2021)
- [Voice Jailbreak Attacks Against GPT-4o](https://mlsanity.com/paper/2405.19103/) (2024)
- [Targeted Adversarial Examples for Black Box Audio Systems](https://mlsanity.com/paper/1805.07820/) (2018)
- [WaveGuard: Understanding and Mitigating Audio Adversarial Examples](https://mlsanity.com/paper/2103.03344/) (2021)
- [Unveiling the Safety of GPT-4o: An Empirical Study using Jailbreak Attacks](https://mlsanity.com/paper/2406.06302/) (2024)
- [AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models](https://mlsanity.com/paper/2412.08608/) (2024)
- [Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models](https://mlsanity.com/paper/2410.23861/) (2024)
- [Enabling Fast and Universal Audio Adversarial Attack Using Generative Model](https://mlsanity.com/paper/2004.12261/) (2020)
- [Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey](https://mlsanity.com/paper/2411.09259/) (2024)
- [Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation](https://mlsanity.com/paper/2410.14425/) (2024)
- [Black-box Adversarial Attacks on Commercial Speech Platforms with Minimal Information](https://mlsanity.com/paper/2110.09714/) (2021)
- [Towards Understanding and Mitigating Audio Adversarial Examples for Speaker Recognition](https://mlsanity.com/paper/2206.03393/) (2022)
- [Defending against Adversarial Audio via Diffusion Model](https://mlsanity.com/paper/2303.01507/) (2023)
- [Going In Style: Audio Backdoors Through Stylistic Transformations](https://mlsanity.com/paper/2211.03117/) (2022)
- [SafeEar: Content Privacy-Preserving Audio Deepfake Detection](https://mlsanity.com/paper/2409.09272/) (2024)
- [Adversarial Music: Real World Audio Adversary Against Wake-word Detection System](https://mlsanity.com/paper/1911.00126/) (2019)
- [Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization](https://mlsanity.com/paper/2505.11217/) (2025)
- [Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2402.12168/) (2024)
- [ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representations](https://mlsanity.com/paper/2312.14398/) (2023)

## Built on by (most cited first, 1 of 1)

- [SmoothGuard: Defending Multimodal Large Language Models with Noise Perturbation and Clustering Aggregation](https://mlsanity.com/paper/2510.26830/) (2025)

## Abstract (arXiv)

Multimodal large language models (MLLMs), which bridge the gap between audio-visual and natural language processing, achieve state-of-the-art performance on several audio-visual tasks. Despite the superior performance of MLLMs, the scarcity of high-quality audio-visual training data and computational resources necessitates the utilization of third-party data and open-source MLLMs, a trend that is increasingly observed in contemporary research. This prosperity masks significant security risks. Empirical studies demonstrate that the latest MLLMs can be manipulated to produce malicious or harmful content. This manipulation is facilitated exclusively through instructions or inputs, including adversarial perturbations and malevolent queries, effectively bypassing the internal security mechanisms embedded within the models. To gain a deeper comprehension of the inherent security vulnerabilities associated with audio-visual-based multimodal models, a series of surveys investigates various types of attacks, including adversarial and backdoor attacks. While existing surveys on audio-visual attacks provide a comprehensive overview, they are limited to specific types of attacks, which lack a unified review of various types of attacks. To address this issue and gain insights into the latest trends in the field, this paper presents a comprehensive and systematic review of audio-visual attacks, which include adversarial attacks, backdoor attacks, and jailbreak attacks. Furthermore, this paper also reviews various types of attacks in the latest audio-visual-based MLLMs, a dimension notably absent in existing surveys. Drawing upon comprehensive insights from a substantial review, this paper delineates both challenges and emergent trends for future research on audio-visual attacks and defense.