Adversarial Attacks in Multimodal Systems: A Practitioner's Survey
arXiv:2505.03084 · doi:10.1109/COMPSAC65507.2025.00222
Abstract
The introduction of multimodal models is a huge step forward in Artificial Intelligence. A single model is trained to understand multiple modalities: text, image, video, and audio. Open-source multimodal models have made these breakthroughs more accessible. However, considering the vast landscape of adversarial attacks across these modalities, these models also inherit vulnerabilities of all the modalities, and ultimately, the adversarial threat amplifies. While broad research is available on possible attacks within or across these modalities, a practitioner-focused view that outlines attack types remains absent in the multimodal world. As more Machine Learning Practitioners adopt, fine-tune, and deploy open-source models in real-world applications, it's crucial that they can view the threat landscape and take the preventive actions necessary. This paper addresses the gap by surveying adversarial attacks targeting all four modalities: text, image, video, and audio. This survey provides a view of the adversarial attack landscape and presents how multimodal adversarial threats have evolved. To the best of our knowledge, this survey is the first comprehensive summarization of the threat landscape in the multimodal world.
Accepted in IEEE COMPSAC 2025
References in corpus (10)
- Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
- ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector
- BadCM: Invisible Backdoor Attack Against Cross-Modal Learning
- Adversarial Attacks on Video Object Segmentation with Hard Region Discovery
- Reinforcement Learning Based Sparse Black-box Adversarial Attack on Video Recognition Models
- Does CLIP Know My Face?
- Certified Robustness to Word Substitution Ranking Attack for Neural Ranking Models
- Introducing Model Inversion Attacks on Automatic Speaker Recognition
- SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems
- Range Membership Inference Attacks