Cover Image

BraveGuard: From Open-World Threats to Safer Computer-Use Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Feng, Yunhao, Ding, Yifan, Du, Xiaohu, Wen, Ming, Deng, Xinhao, Guo, Yanming, Xie, Yuxiang, Zheng, Baihui, Tan, Yingshui, Li, Yige, Wu, Yutao, Wang, Yixu, Cao, Kerui, Huang, Wenke, Ma, Xingjun, Jiang, Yu-Gang
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
by: Feng, Yunhao, et al.
Published: (2026)

BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents
by: Feng, Yunhao, et al.
Published: (2026)

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
by: Feng, Yunhao, et al.
Published: (2026)

BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
by: Li, Juncheng, et al.
Published: (2025)

RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting
by: Jiang, Yilei, et al.
Published: (2024)

Brave Newold World.
by: Rettig, James
Published: (1995)

SentGuard: Sentence-Level Streaming Guardrails for Large Language Models
by: Yu, Jiaqi, et al.
Published: (2026)

Information's Brave New World.
by: Malinconico, S. Michael
Published: (1992)

PaperAsk: A Benchmark for Reliability Evaluation of LLMs in Paper Search and Reading
by: Wu, Yutao, et al.
Published: (2025)

A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5
by: Ma, Xingjun, et al.
Published: (2026)

Smartcards in Libraries: A Brave New World.
by: Myhill, Martin
Published: (1998)

Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models
by: Tan, Yingshui, et al.
Published: (2024)

Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models
by: Zheng, Baihui, et al.
Published: (2025)

Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs
by: Zheng, Xiang, et al.
Published: (2026)

StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data
by: Wang, Yixu, et al.
Published: (2025)

Brave.Net.World: The Internet as a Disinformation Superhighway?
by: Floridi, Luciano
Published: (1996)

Brave Humanism
by: Godfrey, Mollie
Published: (2025)

Ode to the Brave

Extracting Training Data from Unconditional Diffusion Models
by: Chen, Yunhao, et al.
Published: (2024)

Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models
by: Li, Yige, et al.
Published: (2024)

Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
by: Cui, Kaiyuan, et al.
Published: (2026)

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
by: Chen, Yunhao, et al.
Published: (2025)

A Brave New World: The Impact of Technology on Innovation Management
by: Dhruv Grewal, et al.
Published: (2025)

The Governance of Well-being: Towards a “Brave New World”?
by: Alex Romaní Rivera
Published: (2024)

fastml: Guarded Resampling Workflows for Safer Automated Machine Learning in R
by: Korkmaz, Selcuk, et al.
Published: (2026)

ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models
by: Zhao, Yunhan, et al.
Published: (2026)

Position: AI Safety Requires Effective Controllability
by: Li, Yige, et al.
Published: (2026)

Braving Troubled Waters
by: van Ginkel, Rob
Published: (2010)

Brave new family
Published: (1999)

Be Brave by Being Here
by: Julie Stivers
Published: (2023)

PurpCode: Reasoning for Safer Code Generation
by: Liu, Jiawei, et al.
Published: (2025)

New Liouville type theorems for the stationary Navier-Stokes equations
by: Tan, Wenke
Published: (2025)

New Liouville type theorems for the stationary MHD equations in $\mathbb{R}^3$
by: Tan, Wenke
Published: (2025)

Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats
by: Deng, Xinhao, et al.
Published: (2026)

New Technologies and Old-Fashioned Economics: Creating a Brave New World for U.S. Government Information Distribution and Use.
by: Smith, Diane
Published: (1999)

Engineering a Safer World
by: Leveson, Nancy G.
Published: (2019)

HoneypotNet: Backdoor Attacks Against Model Extraction
by: Wang, Yixu, et al.
Published: (2025)

Brave Men / Ernie Pyle
by: Pyle, Ernie
Published: (1939)

Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks
by: Li, Yige, et al.
Published: (2024)

BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks
by: Zhao, Yunhan, et al.
Published: (2024)