Copertina

AgentAuditor: Human-Level Safety and Security Evaluation for LLM Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Luo, Hanjun, Dai, Shenyu, Ni, Chiming, Li, Xinfeng, Zhang, Guibin, Wang, Kun, Liu, Tongliang, Salam, Hanan
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters
di: Luo, Hanjun, et al.
Pubblicazione: (2026)

CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding
di: Luo, Hanjun, et al.
Pubblicazione: (2025)

You Told Me to Do It: Measuring Instructional Text-induced Private Data Leakage in LLM Agents
di: Kao, Ching-Yu, et al.
Pubblicazione: (2026)

The Capability Paradox: How Smarter Auditors Make Multi-Agent Systems Less Secure
di: Liu, Qiqi, et al.
Pubblicazione: (2026)

PrefIx: Understand and Adapt to User Preference in Human-Agent Interaction
di: Li, Jialin, et al.
Pubblicazione: (2026)

Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects
di: Liu, Yixin, et al.
Pubblicazione: (2025)

Beyond One-Size-Fits-All: A Survey of Personalized Affective Computing in Human-Agent Interaction
di: Li, Jialin, et al.
Pubblicazione: (2023)

The Supportiveness-Safety Tradeoff in LLM Well-Being Agents
di: Lalwani, Himanshi, et al.
Pubblicazione: (2026)

"Are You Sure?": An Empirical Study of Human Perception Vulnerability in LLM-Driven Agentic Systems
di: Li, Xinfeng, et al.
Pubblicazione: (2026)

SafePro: Evaluating the Safety of Professional-Level AI Agents
di: Zhou, Kaiwen, et al.
Pubblicazione: (2026)

DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition
di: Luo, Hanjun, et al.
Pubblicazione: (2024)

SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communication
di: Zhang, Ruijia, et al.
Pubblicazione: (2025)

MedSentry: Understanding and Mitigating Safety Risks in Medical LLM Multi-Agent Systems
di: Chen, Kai, et al.
Pubblicazione: (2025)

Supporting Productivity Skill Development in College Students through Social Robot Coaching: A Proof-of-Concept
di: Lalwani, Himanshi, et al.
Pubblicazione: (2025)

Small LLMs Do Not Learn a Generalizable Theory of Mind via Reinforcement Learning
di: Sarangi, Sneheel, et al.
Pubblicazione: (2025)

PSG-Agent: Personality-Aware Safety Guardrail for LLM-based Agents
di: Wu, Yaozu, et al.
Pubblicazione: (2025)

CUAAudit: Meta-Evaluation of Vision-Language Models as Auditors of Autonomous Computer-Use Agents
di: Sumyk, Marta, et al.
Pubblicazione: (2026)

DialogGuard: Multi-Agent Psychosocial Safety Evaluation of Sensitive LLM Responses
di: Luo, Han, et al.
Pubblicazione: (2025)

FairAgent: Democratizing Fairness-Aware Machine Learning with LLM-Powered Agents
di: Dai, Yucong, et al.
Pubblicazione: (2025)

ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces
di: Li, Xiangyi, et al.
Pubblicazione: (2026)

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

Agent Audit: A Security Analysis System for LLM Agent Applications
di: Zhang, Haiyue, et al.
Pubblicazione: (2026)

LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners
di: Zheng, Junhao, et al.
Pubblicazione: (2025)

AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection
di: Luo, Weidi, et al.
Pubblicazione: (2025)

LLM Agents Should Employ Security Principles
di: Zhang, Kaiyuan, et al.
Pubblicazione: (2025)

Decompose-ToM: Enhancing Theory of Mind Reasoning in Large Language Models through Simulation and Task Decomposition
di: Sarangi, Sneheel, et al.
Pubblicazione: (2025)

Agent2Agent Threats in Safety-Critical LLM Assistants: A Human-Centric Taxonomy
di: Stappen, Lukas, et al.
Pubblicazione: (2026)

Efficient LLM Safety Evaluation through Multi-Agent Debate
di: Lin, Dachuan, et al.
Pubblicazione: (2025)

Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents
di: Yehudai, Asaf, et al.
Pubblicazione: (2026)

OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety
di: Vijayvargiya, Sanidhya, et al.
Pubblicazione: (2025)

MATEval: A Multi-Agent Discussion Framework for Advancing Open-Ended Text Evaluation
di: Li, Yu, et al.
Pubblicazione: (2024)

AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents
di: Lu, Junting, et al.
Pubblicazione: (2024)

Simulating Human-Like Learning Dynamics with LLM-Empowered Agents
di: Yuan, Yu, et al.
Pubblicazione: (2025)

SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of Foundation Model-based Embodied Agents
di: Zhan, Simon Sinong, et al.
Pubblicazione: (2025)

AgentAsk: Multi-Agent Systems Need to Ask
di: Lin, Bohan, et al.
Pubblicazione: (2025)

MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents
di: Zhang, Dongsen, et al.
Pubblicazione: (2025)

Scalable Environments Drive Generalizable Agents
di: Zhang, Jiayi, et al.
Pubblicazione: (2026)

Towards Security-Auditable LLM Agents: A Unified Graph Representation
di: Li, Chaofan, et al.
Pubblicazione: (2026)

Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
di: Zhang, Hanrong, et al.
Pubblicazione: (2024)

Measuring Safety Alignment Effects in Autonomous Security Agents
di: David, Isaac, et al.
Pubblicazione: (2026)