# Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers

arXiv: https://arxiv.org/abs/2604.04630 · HTML: https://mlsanity.com/paper/2604.04630/

## 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 47 of its 70 references that are in the map.
- First posted on arXiv 6 Apr 2026.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)
- End-to-end autonomous driving / [Adversarial scenarios and safety testing](https://mlsanity.com/driving/adversarial-scenarios-and-safety-testing/)
- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)

## Builds on (most cited first, 30 of 47)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023)
- [DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model](https://mlsanity.com/paper/2310.01412/) (2023)
- [Hidden Trigger Backdoor Attacks](https://mlsanity.com/paper/1910.00033/) (2019)
- [Invisible Backdoor Attack with Sample-Specific Triggers](https://mlsanity.com/paper/2012.03816/) (2020)
- [Visual Adversarial Examples Jailbreak Aligned Large Language Models](https://mlsanity.com/paper/2306.13213/) (2023)
- [Data Poisoning Attacks Against Federated Learning Systems](https://mlsanity.com/paper/2007.08432/) (2020)
- [BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning](https://mlsanity.com/paper/2311.12075/) (2023)
- [Transferable Adversarial Attacks for Image and Video Object Detection](https://mlsanity.com/paper/1811.12641/) (2018)
- [Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt](https://mlsanity.com/paper/2406.04031/) (2024)
- [Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection](https://mlsanity.com/paper/2201.08970/) (2022)
- [Efficient Adversarial Attacks for Visual Object Tracking](https://mlsanity.com/paper/2008.00217/) (2020)
- [A Large-scale Multiple-objective Method for Black-box Attack against Object Detection](https://mlsanity.com/paper/2209.07790/) (2022)
- [Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs](https://mlsanity.com/paper/2402.14872/) (2024)
- [Multi-Frame, Lightweight & Efficient Vision-Language Models for Question Answering in Autonomous Driving](https://mlsanity.com/paper/2403.19838/) (2024)
- [Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models](https://mlsanity.com/paper/2402.06659/) (2024)
- [Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift](https://mlsanity.com/paper/2406.18844/) (2024)
- [SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation](https://mlsanity.com/paper/2312.04913/) (2023)
- [Pre-trained Trojan Attacks for Visual Recognition](https://mlsanity.com/paper/2312.15172/) (2023)
- [Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection](https://mlsanity.com/paper/2402.11473/) (2024)
- [Diversifying the High-level Features for better Adversarial Transferability](https://mlsanity.com/paper/2304.10136/) (2023)
- [Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning](https://mlsanity.com/paper/2403.16257/) (2024)
- [Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack](https://mlsanity.com/paper/2405.16134/) (2024)
- [Towards Robust Physical-world Backdoor Attacks on Lane Detection](https://mlsanity.com/paper/2405.05553/) (2024)

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

- [Rethinking Language's Role in Efficient VLA for Autonomous Vehicles: Toward Smarter, Trustworthy Driving](https://mlsanity.com/paper/2608.30144/) (2026)

## Abstract (arXiv)

Visual language model (VLM) is rapidly being integrated into safety-critical systems such as autonomous driving, making it an important attack surface for potential backdoor attacks. Existing backdoor attacks mainly rely on unimodal, explicit, and easily detectable triggers, making it difficult to construct both covert and stable attack channels in autonomous driving scenarios. GLA introduces two naturalistic triggers: graffiti-based visual patterns generated via stable diffusion inpainting, which seamlessly blend into urban scenes, and cross-language text triggers, which introduce distributional shifts while maintaining semantic consistency to build robust language-side trigger signals. Experiments on DriveVLM show that GLA requires only a 10% poisoning ratio to achieve a 90% Attack Success Rate (ASR) and a 0% False Positive Rate (FPR). More insidiously, the backdoor does not weaken the model on clean tasks, but instead improves metrics such as BLEU-1, making it difficult for traditional performance-degradation-based detection methods to identify the attack. This study reveals underestimated security threats in self-driving VLMs and provides a new attack paradigm for backdoor evaluation in safety-critical multimodal systems.