The paper investigates how multimodal large language models are more susceptible to prompt injection when adversarial instructions are presented as text rather than as non-textual inputs like images. It proposes a training‑free defense that renders untrusted payloads into typographic images (or audio) before they reach the model, a method called Pictionary. Experiments on ten models and two benchmarks show that this approach significantly lowers attack success rates while maintaining normal functionality, and that fine‑tuning on image‑rendered instructions can further reduce the modality gap.
By Jie Zhang, Andrei Baroian, Jan N. van Rijn, Avital Shafran, Florian Tram\`{e}r
The paper investigates how Vision Language Models (VLMs) can be fooled by tiny, human‑imperceptible changes to images. It introduces a gradient‑based attack that targets only the vision encoder, reducing computational cost while still effectively disrupting both untargeted and targeted multimodal interpretations. Experiments on open‑source VLMs such as Qwen2.5‑VL, Granite‑Vision, FastVLM, and Phi‑3.5‑Vision demonstrate that these small perturbations can dramatically alter the models’ textual outputs.
The paper investigates how Vision Language Models (VLMs) can be fooled by small, human‑imperceptible changes to images. It introduces a gradient‑based attack that targets only the vision encoder, reducing computational cost while still effectively disrupting both untargeted and targeted multimodal alignment. Experiments on open‑source VLMs such as Qwen2.5‑VL, Granite‑Vision, FastVLM, and Phi‑3.5‑Vision demonstrate that these perturbations can significantly alter the models’ textual outputs.
By Ilan Zini, Boussad Addad, Katarzyna Kapusta
arXiv:2511.18921v2 Announce Type: replace
Abstract: Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously ac...
By Juncheng Li, Yige Li, Hanxun Huang, Yunhao Chen, Xin Wang, Yixu Wang, Xingjun Ma, Yu-Gang Jiang
arXiv:2604. 05809v2 Announce Type: replace-cross Abstract: This paper presents Text-Guided Backdoor (TGB), an adjustable backdoor attack against multimodal pretrained models that uses natural-word triggers, namely words that can naturally occur in ordinary textual inputs.
By Yiyang Zhang, Chaojian Yu, Ziming Hong, Yuanjie Shao, Qinmu Peng, Tongliang Liu, Xinge You
arXiv:2602. 10179v2 Announce Type: replace-cross Abstract: Recent advances in large image editing models have shifted the paradigm from text-driven instructions to vision-prompt editing, where user intent is inferred directly from visual inputs such as marks, arrows, and visual-text prompts.
By Jiacheng Hou, Yining Sun, Ruochong Jin, Haochen Han, Fangming Liu, Wai Kin Victor Chan, Alex Jinpeng Wang
arXiv:2605. 25194v2 Announce Type: replace Abstract: Adversarial images pose a severe security threat to multimodal large language models through prompt injection.
By Dongpeng Zhang, Ke Ma, Yangbangyan Jiang, Gaozheng Pei, Longtao Huang, Qianqian Xu, Qingming Huang
Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e. g.
Vis-Poison is a novel attack that poisons multimodal retrieval-augmented generation systems by inserting attacker-controlled images as visual evidence, without altering any textual metadata. The attack uses an automated multi-agent approach to create visually plausible poisoned images and has been tested on two multimodal RAG pipelines, four embedding models, and six generation models. In black-box settings, Vis-Poison achieves an end-to-end success rate between 40.16% and 65.40% against 30,000-entry knowledge bases, and remains effective against various multimodal large language models with an average success rate above 60%.
By Rujin Liang, Zhongpu Chen, Yuhao Lei, Xin Miao
The paper introduces a new adversarial attack on multimodal large language models (MLLMs) that targets the models’ intrinsic focus in the frequency domain. By exploiting the models’ sensitivity to phase information, the authors design a phase‑aware perturbation strategy that restricts changes to structure‑relevant phase regions, making attacks both effective and imperceptible. An auxiliary adversarial prompt module further misaligns multimodal attention toward targeted structural patterns, and experiments on several MLLM models and datasets confirm the method’s superior performance over existing attacks.
By Daizong Liu, Junhao Dong, Zhiyuan Ma, Xiaoye Qu, Xiang Fang, Runwei Guan, Keke Tang, Jianfeng Dong, Yew-Soon Ong
arXiv:2604. 05853v3 Announce Type: replace Abstract: Modern text-to-image (T2I) models can now render legible, paragraph-length text, enabling a fundamentally new class of misuse.
By Zonghao Ying, Haowen Dai, Lianyu Hu, Zonglei Jing, Quanchen Zou, Yaodong Yang, Aishan Liu, Xianglong Liu
arXiv:2410. 00296v2 Announce Type: replace Abstract: Vision-language Models (VLMs) are essential for contextual understanding of both visual and textual information.
By Junlin Fang, Wenyu Chen, Reshmi Ghosh, Robert Sim, Ahmed Salem, Vitor R. Carvalho, Emily Lawton, Sharon Li, Jack W. Stokes, Sean Du