Copertina

MalURLBench: A Benchmark Evaluating Agents' Vulnerabilities When Processing Web URLs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kong, Dezhang, Wu, Zhuxi, Liu, Shiqi, Tan, Zhicheng, Lu, Kuichen, Li, Minghao, Liu, Qichen, Chu, Shengyu, Xu, Zhenhua, Liu, Xuan, Han, Meng
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Cryptography and Security Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Fingerprint Vector: Enabling Scalable and Efficient Model Fingerprint Transfer via Vector Addition
di: Xu, Zhenhua, et al.
Pubblicazione: (2024)

Web Fraud Attacks Against LLM-Driven Multi-Agent Systems
di: Kong, Dezhang, et al.
Pubblicazione: (2025)

AttnDiff: Attention-based Differential Fingerprinting for Large Language Models
di: Zhang, Haobo, et al.
Pubblicazione: (2026)

Scalpel-SAM: A Semi-Supervised Paradigm for Adapting SAM to Infrared Small Object Detection
di: Liu, Zihan, et al.
Pubblicazione: (2025)

Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends
di: Xu, Zhenhua, et al.
Pubblicazione: (2025)

DNF: Dual-Layer Nested Fingerprinting for Large Language Model Intellectual Property Protection
di: Xu, Zhenhua, et al.
Pubblicazione: (2026)

WebCanvas: Benchmarking Web Agents in Online Environments
di: Pan, Yichen, et al.
Pubblicazione: (2024)

When Agent Markets Arrive
di: Liu, Xuan, et al.
Pubblicazione: (2026)

LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?
di: Liu, Bin, et al.
Pubblicazione: (2025)

When Bots Take the Bait: Exposing and Mitigating the Emerging Social Engineering Attack in Web Automation Agent
di: Wu, Xinyi, et al.
Pubblicazione: (2026)

EconWebArena: Benchmarking Autonomous Agents on Economic Tasks in Realistic Web Environments
di: Liu, Zefang, et al.
Pubblicazione: (2025)

A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures
di: Kong, Dezhang, et al.
Pubblicazione: (2025)

DomURLs_BERT: Pre-trained BERT-based Model for Malicious Domains and URLs Detection and Classification
di: Mahdaouy, Abdelkader El, et al.
Pubblicazione: (2024)

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models
di: Zhou, Yi, et al.
Pubblicazione: (2025)

Parsing Millions of URLs per Second
di: Nizipli, Yagiz, et al.
Pubblicazione: (2023)

Keyword Identification within Greek URLs
di: Maria-Alexandra Vonitsanou
Pubblicazione: (2011)

Unlearning Concepts from Text-to-Video Diffusion Models
di: Liu, Shiqi, et al.
Pubblicazione: (2024)

ForgetMark: Stealthy Fingerprint Embedding via Targeted Unlearning in Language Models
di: Xu, Zhenhua, et al.
Pubblicazione: (2026)

Longitudinal Sampling of URLs From the Wayback Machine
di: Garg, Kritika, et al.
Pubblicazione: (2025)

Automated Phishing Detection Using URLs and Webpages
di: Wang, Huilin, et al.
Pubblicazione: (2024)

GUI-PRA: Process Reward Agent for GUI Tasks
di: Xiong, Tao, et al.
Pubblicazione: (2025)

SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents
di: Ying, Zonghao, et al.
Pubblicazione: (2025)

When the Specification Emerges: Benchmarking Faithfulness Loss in Long-Horizon Coding Agents
di: Yan, Lu, et al.
Pubblicazione: (2026)

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

URLs in the OPAC: Integrating or Disintegrating Research Libraries' Catalogs
di: Burke, Gerald, et al.
Pubblicazione: (2003)

HarmonyGuard: Toward Safety and Utility in Web Agents via Adaptive Policy Enhancement and Dual-Objective Optimization
di: Chen, Yurun, et al.
Pubblicazione: (2025)

CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities
di: Zhu, Yuxuan, et al.
Pubblicazione: (2025)

Quantum Process Tomography of a Thermal Alkali-Metal Vapor
di: Sun, Yujie, et al.
Pubblicazione: (2025)

Regulation of the HMGA2‐SNAI2/CXCR4 axis in atherosclerosis and retinal neovascularization: new therapeutic insights
di: Jianan Li, et al.
Pubblicazione: (2024)

BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese
di: Zhou, Peilin, et al.
Pubblicazione: (2025)

World-Model-Augmented Web Agents with Action Correction
di: Shen, Zhouzhou, et al.
Pubblicazione: (2026)

Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining
di: Fan, Dongyang, et al.
Pubblicazione: (2025)

Discrete Differential Principle for Continuous Smooth Function Representation
di: Wang, Guoyou, et al.
Pubblicazione: (2025)

When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents
di: Liu, Shi, et al.
Pubblicazione: (2026)

Towards Robust and Secure Embodied AI: A Survey on Vulnerabilities and Attacks
di: Xing, Wenpeng, et al.
Pubblicazione: (2025)

DailyQA: A Benchmark to Evaluate Web Retrieval Augmented LLMs Based on Capturing Real-World Changes
di: Cheng, Jiehan, et al.
Pubblicazione: (2025)

Natto_asMDin_alloXO
di: Liu, Minghao
Pubblicazione: (2025)

Improved Monte Carlo Planning via Causal Disentanglement for Structurally-Decomposed Markov Decision Processes
di: Liu, Larkin, et al.
Pubblicazione: (2024)

WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance
di: Liu, Genglin, et al.
Pubblicazione: (2025)

Homologically area-minimizing surfaces mod $v$ have at worst codimension 2 singular sets asymptotically
di: Liu, Zhenhua
Pubblicazione: (2024)