mlsanityData to 14 Oct 2026

Adversarial Attacks in Multimodal Systems: A Practitioner's Survey

arXiv 2505.03084 ↗First posted 6 May 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 77 of its 95 references that are in the map. First posted on arXiv 6 May 2025.

Builds on

77 of 95 references.

References · 77

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  7. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  8. 2020Extracting Training Data from Large Language Modelscited by 2,189
  9. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  10. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  11. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,429
  12. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
38 more
  1. 2019Deep Leakage from Gradientscited by 1,021
  2. 2024Gemma: Open Models Based on Gemini Research and Technologycited by 916
  3. 2021Membership Inference Attacks From First Principlescited by 878
  4. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  5. 2023Extracting Training Data from Diffusion Modelscited by 732
  6. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 722
  7. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 671
  8. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 546
  9. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 519
  10. 2017Adversarial Patchcited by 517
  11. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 498
  12. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  13. 2018Generating Natural Language Adversarial Examplescited by 424
  14. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 349
  15. 2018Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifierscited by 345
  16. 2020Weight Poisoning Attacks on Pre-trained Modelscited by 341
  17. 2018Adversarial Example Generation with Syntactically Controlled Paraphrase Networkscited by 286
  18. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 274
  19. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 246
  20. 2019A backdoor attack against LSTM-based text classification systemscited by 227
  21. 2021Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Triggercited by 222
  22. 2023SneakyPrompt: Jailbreaking Text-to-image Generative Modelscited by 189
  23. 2024Security and Privacy Challenges of Large Language Models: A Surveycited by 186
  24. 2020Clean-Label Backdoor Attacks on Video Recognition Modelscited by 169
  25. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
  26. 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 155
  27. 2018DPatch: An Adversarial Patch Attack on Object Detectorscited by 147
  28. 2020Backdoor Attacks Against Deep Learning Systems in the Physical Worldcited by 134
  29. 2020Adversarial Camouflage: Hiding Physical-World Attacks with Natural Stylescited by 126
  30. 2019Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognitioncited by 124
  31. 2023Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMscited by 124
  32. 2018LaVAN: Localized and Visible Adversarial Noisecited by 113
  33. 2022How to Backdoor Diffusion Models?cited by 104
  34. 2024A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trendscited by 84
  35. 2023Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Modelscited by 75
  36. 2023Black Box Adversarial Prompting for Foundation Modelscited by 62
  37. 2018Sparse Adversarial Perturbations for Videoscited by 57
  38. 2024PAL: Proxy-Guided Black-Box Attack on Large Language Modelscited by 50

50 most cited of 77 All 77 (JSON)

Built on by

Not cited yet.