Image de couverture de livre

Too Helpful to Be Safe: User-Mediated Attacks on Planning and Web-Use Agents

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Fengchao, Wu, Tingmin, Nguyen, Van, Rudolph, Carsten
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SoK: Exposing the Generation and Detection Gaps in LLM-Generated Phishing
par: Chen, Fengchao, et autres
Publié: (2025)

PEEK: Phishing Evolution Framework for Phishing Generation and Evolving Pattern Analysis using Large Language Models
par: Chen, Fengchao, et autres
Publié: (2024)

MulVuln: Enhancing Pre-trained LMs with Shared and Language-Specific Knowledge for Multilingual Vulnerability Detection
par: Nguyen, Van, et autres
Publié: (2025)

Deep Learning-Based Out-of-distribution Source Code Data Identification: How Far Have We Gone?
par: Nguyen, Van, et autres
Publié: (2024)

An Innovative Information Theory-based Approach to Tackle and Enhance The Transparency in Phishing Detection
par: Nguyen, Van, et autres
Publié: (2024)

Can Current Detectors Catch Face-to-Voice Deepfake Attacks?
par: Nguyen, Nguyen Linh Bao, et autres
Publié: (2025)

WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents
par: Chen, Yulin, et autres
Publié: (2026)

Too Private to Tell: Practical Token Theft Attacks on Apple Intelligence
par: Zhou, Haoling, et autres
Publié: (2026)

Mind the Web: The Security of Web Use Agents
par: Shapira, Avishag, et autres
Publié: (2025)

SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents
par: Yin, Sheng, et autres
Publié: (2024)

PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks
par: Feng, Chen, et autres
Publié: (2024)

CyberSleuth: Autonomous Blue-Team LLM Agent for Web Attack Forensics
par: Fumero, Stefano, et autres
Publié: (2025)

ThreatModeling-LLM: Automating Threat Modeling using Large Language Models for Banking System
par: Wu, Tingmin, et autres
Publié: (2024)

URL Inspection Tasks: Helping Users Detect Phishing Links in Emails
par: Lain, Daniele, et autres
Publié: (2025)

User Profiles: The Achilles' Heel of Web Browsers
par: Somé, Dolière Francis, et autres
Publié: (2025)

When Bots Take the Bait: Exposing and Mitigating the Emerging Social Engineering Attack in Web Automation Agent
par: Wu, Xinyi, et autres
Publié: (2026)

SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants
par: Wang, Haoyu, et autres
Publié: (2026)

WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
par: Evtimov, Ivan, et autres
Publié: (2025)

OMNIINTENT: A Trusted Intent-Centric Framework for User-Friendly Web3
par: Pan, Zhuoran, et autres
Publié: (2026)

WebSentinel: Detecting and Localizing Prompt Injection Attacks for Web Agents
par: Wang, Xilong, et autres
Publié: (2026)

WIPI: A New Web Threat for LLM-Driven Web Agents
par: Wu, Fangzhou, et autres
Publié: (2024)

WebPII: Benchmarking Visual PII Detection for Computer-Use Agents
par: Zhao, Nathan
Publié: (2026)

That Doesn't Go There: Attacks on Shared State in Multi-User Augmented Reality Applications
par: Slocum, Carter, et autres
Publié: (2023)

WADBERT: Dual-channel Web Attack Detection Based on BERT Models
par: Luo, Kangqiang, et autres
Publié: (2026)

WebTrap Park: An Automated Platform for Systematic Security Evaluation of Web Agents
par: Wu, Xinyi, et autres
Publié: (2026)

Exploring and Exploiting the Resource Isolation Attack Surface of WebAssembly Containers
par: Yu, Zhaofeng, et autres
Publié: (2025)

Stealing Trust: Unraveling Blind Message Attacks in Web3 Authentication
par: Yan, Kailun, et autres
Publié: (2024)

Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents
par: Zou, Wei, et autres
Publié: (2026)

VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents
par: Cao, Tri, et autres
Publié: (2025)

PINA: Prompt Injection Attack against Navigation Agents
par: Liu, Jiani, et autres
Publié: (2026)

AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents
par: Hu, Haitao, et autres
Publié: (2025)

Are Enterprises Ready for Quantum-Safe Cybersecurity?
par: Le, Tran Duc, et autres
Publié: (2025)

TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning
par: Zhang, Mingxuan, et autres
Publié: (2025)

HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities
par: Ren, Xiaoxue, et autres
Publié: (2025)

Agent Meltdowns: The Road to Hell Is Paved with Helpful Agents
par: Jha, Rishi, et autres
Publié: (2026)

Detecting Zero-Day Web Attacks with an Ensemble of LSTM, GRU, and Stacked Autoencoders
par: Babaey, Vahid, et autres
Publié: (2025)

Investigating Vulnerabilities of GPS Trip Data to Trajectory-User Linking Attacks
par: Ströbl, Benedikt, et autres
Publié: (2025)

Attention Masks Help Adversarial Attacks to Bypass Safety Detectors
par: Shi, Yunfan
Publié: (2024)

MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks
par: Syros, Georgios, et autres
Publié: (2026)

Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree
par: Johnson, Sam, et autres
Publié: (2025)