# Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models

arXiv: https://arxiv.org/abs/2410.06699 · HTML: https://mlsanity.com/paper/2410.06699/

## Key facts

- Cited by 27 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 26 of its 44 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day](https://mlsanity.com/paper/2306.00890/) (2023)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models](https://mlsanity.com/paper/1708.03999/) (2017)
- [LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model](https://mlsanity.com/paper/2304.15010/) (2023)
- [Otter: A Multi-Modal Model with In-Context Instruction Tuning](https://mlsanity.com/paper/2305.03726/) (2023)
- [mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration](https://mlsanity.com/paper/2311.04257/) (2023)
- [Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples](https://mlsanity.com/paper/1605.07277/) (2016)
- [Are aligned neural networks adversarially aligned?](https://mlsanity.com/paper/2306.15447/) (2023)
- [Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models](https://mlsanity.com/paper/2307.14539/) (2023)
- [mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections](https://mlsanity.com/paper/2205.12005/) (2022)
- [On the Robustness of Vision Transformers to Adversarial Examples](https://mlsanity.com/paper/2104.02610/) (2021)
- [On the Adversarial Robustness of Multi-Modal Foundation Models](https://mlsanity.com/paper/2308.10741/) (2023)
- [Towards Adversarial Attack on Vision-Language Pre-training Models](https://mlsanity.com/paper/2206.09391/) (2022)
- [On the Robustness of Large Multimodal Models Against Image Adversarial Attacks](https://mlsanity.com/paper/2312.03777/) (2023)
- [Human-Adversarial Visual Question Answering](https://mlsanity.com/paper/2106.02280/) (2021)
- [Controlled Caption Generation for Images Through Adversarial Attacks](https://mlsanity.com/paper/2107.03050/) (2021)

## Built on by (most cited first, 27 of 27)

- [Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks](https://mlsanity.com/paper/2502.13175/) (2025)
- [ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agents](https://mlsanity.com/paper/2509.16645/) (2025)
- [Exploiting Vision Encoder Vulnerabilities for Universal Adversarial Perturbations on Large Vision-Language Models](https://mlsanity.com/paper/2412.08108/) (2024)
- [AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization](https://mlsanity.com/paper/2504.01735/) (2025)
- [VEAttack: Downstream-agnostic Vision Encoder Attack against Large Vision Language Models](https://mlsanity.com/paper/2505.17440/) (2025)
- [On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression](https://mlsanity.com/paper/2601.21531/) (2026)
- [Tracking the Copyright of Large Vision-Language Models through Parameter Learning Adversarial Images](https://mlsanity.com/paper/2502.16593/) (2025)
- [Enhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projector](https://mlsanity.com/paper/2508.13739/) (2025)
- [Seeing is Deceiving: Exploitation of Visual Pathways in Multi-Modal Language Models](https://mlsanity.com/paper/2411.05056/) (2024)
- [Adversarial Attacks on Multimodal Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2603.27918/) (2026)
- [A Satellite-Ground Synergistic Large Vision-Language Model System for Earth Observation](https://mlsanity.com/paper/2507.05731/) (2025)
- [PA-Attack: Guiding Gray-Box Attacks on LVLM Vision Encoders with Prototypes and Attention](https://mlsanity.com/paper/2602.19418/) (2026)
- [High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models](https://mlsanity.com/paper/2512.21815/) (2025)
- [Grounding-Driven Attack: Improving Encoder-based Adversarial Transferability against Large Vision-Language Models](https://mlsanity.com/paper/2602.09431/) (2026)
- [Adversarial Attacks Against MLLMs via Progressive Resolution Processing and Adaptive Feature Alignment](https://mlsanity.com/paper/2605.09902/) (2026)
- [Revisiting CroPA: A Reproducibility Study and Enhancements for Cross-Prompt Adversarial Transferability in Vision-Language Models](https://mlsanity.com/paper/2506.22982/) (2025)
- [Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM](https://mlsanity.com/paper/2507.20994/) (2025)
- [Vision Token Masking Alone Cannot Prevent PHI Leakage in Medical Document OCR: A Systematic Evaluation](https://mlsanity.com/paper/2511.18272/) (2025)
- [On the Adversarial Robustness of 3D Large Vision-Language Models](https://mlsanity.com/paper/2601.06464/) (2026)
- [Feature-Space Smoothing: Certified Robustness of Deep Representations](https://mlsanity.com/paper/2601.16200/) (2026)
- [SGHA-Attack: Semantic-Guided Hierarchical Alignment for Transferable Targeted Attacks on Vision-Language Models](https://mlsanity.com/paper/2602.01574/) (2026)
- [Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluation](https://mlsanity.com/paper/2602.23117/) (2026)
- [All Vehicles Can Lie: Efficient Adversarial Defense in Fully Untrusted-Vehicle Collaborative Perception via Pseudo-Random Bayesian Inference](https://mlsanity.com/paper/2603.08498/) (2026)
- [Covert Visual Prompt Injection against Commercial Multimodal Large Language Models](https://mlsanity.com/paper/2603.29418/) (2026)
- [Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards](https://mlsanity.com/paper/2608.07535/) (2026)
- [It Takes Little to Rewrite Perception: Targeted Semantic Substitution in Vision-Language Models at ε≤ 4/255](https://mlsanity.com/paper/2609.38298/) (2026)
- [Feature-Aware Token Attack for Compression-Triggered Stealthy Failures in Large Vision-Language Models](https://mlsanity.com/paper/2609.39134/) (2026)

## Abstract (arXiv)

Large vision-language models (LVLMs) integrate visual information into large language models, showcasing remarkable multi-modal conversational capabilities. However, the visual modules introduces new challenges in terms of robustness for LVLMs, as attackers can craft adversarial images that are visually clean but may mislead the model to generate incorrect answers. In general, LVLMs rely on vision encoders to transform images into visual tokens, which are crucial for the language models to perceive image contents effectively. Therefore, we are curious about one question: Can LVLMs still generate correct responses when the encoded visual tokens are attacked and disrupting the visual information? To this end, we propose a non-targeted attack method referred to as VT-Attack (Visual Tokens Attack), which constructs adversarial examples from multiple perspectives, with the goal of comprehensively disrupting feature representations and inherent relationships as well as the semantic properties of visual tokens output by image encoders. Using only access to the image encoder in the proposed attack, the generated adversarial examples exhibit transferability across diverse LVLMs utilizing the same image encoder and generality across different tasks. Extensive experiments validate the superior attack performance of the VT-Attack over baseline methods, demonstrating its effectiveness in attacking LVLMs with image encoders, which in turn can provide guidance on the robustness of LVLMs, particularly in terms of the stability of the visual feature space.