:: Library Catalog

Cover Image

Saved in:

Bibliographic Details
Main Authors:	Feng, Yunhao, Ding, Yifan, Tan, Yingshui, Ma, Xingjun, Li, Yige, Wu, Yutao, Gao, Yifeng, Zhai, Kun, Guo, Yanming
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	https://arxiv.org/abs/2604.02947
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

BraveGuard: From Open-World Threats to Safer Computer-Use Agents
by: Feng, Yunhao, et al.
Published: (2026)

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

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

Identity Lock: Locking API Fine-tuned LLMs With Identity-based Wake Words
by: Su, Hongyu, et al.
Published: (2025)

ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checking
by: Wu, Yutao, et al.
Published: (2025)

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

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
by: Kuntz, Thomas, et al.
Published: (2025)

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

Human-Guided Harm Recovery for Computer Use Agents
by: Li, Christy, et al.
Published: (2026)

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
by: Andriushchenko, Maksym, et al.
Published: (2024)

Internal Safety Collapse in Frontier Large Language Models
by: Wu, Yutao, et al.
Published: (2026)

BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
by: Li, Yige, et al.
Published: (2024)

AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions
by: Ying, Zonghao, et al.
Published: (2025)

HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models
by: Chen, Zixing, et al.
Published: (2026)

AutoBackdoor: Automating Backdoor Attacks via LLM Agents
by: Li, Yige, 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)

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

FedEGG: Federated Learning with Explicit Global Guidance
by: Zhai, Kun, et al.
Published: (2024)

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

When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents
by: Jones, Jaylen, et al.
Published: (2026)

Beyond Surface Judgments: Human-Grounded Risk Evaluation of LLM-Generated Disinformation
by: Xu, Zonghuan, et al.
Published: (2026)

Mirror: A Multi-Agent System for AI-Assisted Ethics Review
by: Ding, Yifan, et al.
Published: (2026)

Measuring Harmfulness of Computer-Using Agents
by: Tian, Aaron Xuxiang, et al.
Published: (2025)

SusBench: An Online Benchmark for Evaluating Dark Pattern Susceptibility of Computer-Use Agents
by: Guo, Longjie, et al.
Published: (2025)

AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models
by: Zhang, Jiaming, et al.
Published: (2024)

HarmRLVR: Weaponizing Verifiable Rewards for Harmful LLM Alignment
by: Liu, Yuexiao, et al.
Published: (2025)

FedAPT: Federated Adversarial Prompt Tuning for Vision-Language Models
by: Zhai, Kun, et al.
Published: (2025)

AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models
by: Li, Jiayu, et al.
Published: (2025)

SIDE: Surrogate Conditional Data Extraction from Diffusion Models
by: Chen, Yunhao, et al.
Published: (2024)

X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
by: Huang, Hanxun, et al.
Published: (2025)

Detecting Backdoor Samples in Contrastive Language Image Pretraining
by: Huang, Hanxun, et al.
Published: (2025)

OOD-MMSafe: Advancing MLLM Safety from Harmful Intent to Hidden Consequences
by: Wen, Ming, et al.
Published: (2026)

OpenComputer: Verifiable Software Worlds for Computer-Use Agents
by: Wei, Jinbiao, et al.
Published: (2026)

The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
by: Ding, Xuwei, et al.
Published: (2026)

AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions
by: Sun, Jingwei, et al.
Published: (2026)

OSWorld-Human: Benchmarking the Efficiency of Computer-Use Agents
by: Abhyankar, Reyna, et al.
Published: (2025)

SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents
by: Shen, Yujiong, et al.
Published: (2026)

BrokenVideos: A Benchmark Dataset for Fine-Grained Artifact Localization in AI-Generated Videos
by: Lin, Jiahao, et al.
Published: (2025)

SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents
by: Ding, Yifeng, et al.
Published: (2026)