Cover Image

WebInject: Prompt Injection Attack to Web Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Xilong, Bloch, John, Shao, Zedian, Hu, Yuepeng, Zhou, Shuyan, Gong, Neil Zhenqiang
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection
by: Shao, Zedian, et al.
Published: (2026)

Refusing Safe Prompts for Multi-modal Large Language Models
by: Shao, Zedian, et al.
Published: (2024)

Automatically Generating Visual Hallucination Test Cases for Multimodal Large Language Models
by: Liu, Zhongye, et al.
Published: (2024)

WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents
by: Liu, Yinuo, et al.
Published: (2025)

Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment
by: Shao, Zedian, et al.
Published: (2024)

WebSentinel: Detecting and Localizing Prompt Injection Attacks for Web Agents
by: Wang, Xilong, et al.
Published: (2026)

Jailbreaking Safeguarded Text-to-Image Models via Large Language Models
by: Jiang, Zhengyuan, et al.
Published: (2025)

Watermark-based Attribution of AI-Generated Content
by: Jiang, Zhengyuan, et al.
Published: (2024)

Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos
by: Yu, Shoubin, et al.
Published: (2026)

MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation
by: Li, Yan, et al.
Published: (2026)

WebGuard: Building a Generalizable Guardrail for Web Agents
by: Zheng, Boyuan, et al.
Published: (2025)

InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training
by: Zhang, Ziyun, et al.
Published: (2026)

SafeText: Safe Text-to-image Models via Aligning the Text Encoder
by: Hu, Yuepeng, et al.
Published: (2025)

VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks
by: Koh, Jing Yu, et al.
Published: (2024)

Web World Models
by: Feng, Jichen, et al.
Published: (2025)

SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills
by: Zheng, Boyuan, et al.
Published: (2025)

OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
by: Yang, Rui, et al.
Published: (2026)

VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search
by: Jia, Yiming, et al.
Published: (2025)

TimeWarp: Evaluating Web Agents by Revisiting the Past
by: Ishmam, Md Farhan, et al.
Published: (2026)

Dual-View Visual Contextualization for Web Navigation
by: Kil, Jihyung, et al.
Published: (2024)

Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence
by: Hong, Yining, et al.
Published: (2025)

IW-Bench: Evaluating Large Multimodal Models for Converting Image-to-Web
by: Guo, Hongcheng, et al.
Published: (2024)

Tur[k]ingBench: A Challenge Benchmark for Web Agents
by: Xu, Kevin, et al.
Published: (2024)

GPT-4V(ision) is a Generalist Web Agent, if Grounded
by: Zheng, Boyuan, et al.
Published: (2024)

When Think-with-Image Meets Safety: What Determines Multimodal Jailbreak Robustness?
by: Tian, Yuan, et al.
Published: (2026)

Physical Prompt Injection Attacks on Large Vision-Language Models
by: Ling, Chen, et al.
Published: (2026)

RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World Users
by: Ye, Suyu, et al.
Published: (2025)

MERRIN: A Benchmark for Multimodal Evidence Retrieval and Reasoning in Noisy Web Environments
by: Wang, Han, et al.
Published: (2026)

OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web
by: Kapoor, Raghav, et al.
Published: (2024)

SODIUM: From Open Web Data to Queryable Databases
by: Hu, Chuxuan, et al.
Published: (2026)

Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents
by: Luo, Yaxin, et al.
Published: (2025)

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
by: Zhou, Andy, et al.
Published: (2024)

Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs
by: Yun, Sukmin, et al.
Published: (2024)

Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters
by: Xu, Zhiyu, et al.
Published: (2026)

Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models
by: Zhou, Qiji, et al.
Published: (2024)

WebSight: A Vision-First Architecture for Robust Web Agents
by: Bhathal, Tanvir, et al.
Published: (2025)

Text Prompt Injection of Vision Language Models
by: Zhu, Ruizhe
Published: (2025)

Vision Learners Meet Web Image-Text Pairs
by: Zhao, Bingchen, et al.
Published: (2023)

TP-Eval: Tap Multimodal LLMs' Potential in Evaluation by Customizing Prompts
by: Xie, Yuxuan, et al.
Published: (2024)

Adversarial Prompt Injection Attack on Multimodal Large Language Models
by: Ding, Meiwen, et al.
Published: (2026)