Imagen de Portada

MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhou, Zhenhong, Zhang, Yuanhe, Cai, Hongwei, Aloqaily, Moayad, Bouachir, Ouns, Pang, Linsey, Mehrotra, Prakhar, Wang, Kun, Wen, Qingsong
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models
por: Lin, Liang, et al.
Publicado: (2025)

Blockchain-enabled Energy Trading and Battery-based Sharing in Microgrids
por: Zekiye, Abdulrezzak, et al.
Publicado: (2024)

ED-DAO: Energy Donation Algorithms based on Decentralized Autonomous Organization
por: Zekiye, Abdulrezzak, et al.
Publicado: (2025)

Generative AI for Networking
por: Zaman, Faisal, et al.
Publicado: (2025)

Analysis of Blockchain Assisted Energy Sharing Algorithms with Realistic Data Across Microgrids
por: Zekiye, Abdulrezzak, et al.
Publicado: (2024)

Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models
por: Yu, Miao, et al.
Publicado: (2025)

SafeSeek: Universal Attribution of Safety Circuits in Language Models
por: Yu, Miao, et al.
Publicado: (2026)

Editorial for the IJNM Special Issue From the Best Papers of IEEE ICBC 2023 “Advancing Blockchain and Cryptocurrency”
por: Laura Ricci, et al.
Publicado: (2024)

ChronosAudio: A Comprehensive Long-Audio Benchmark for Evaluating Audio-Large Language Models
por: Luo, Kaiwen, et al.
Publicado: (2026)

HearSay Benchmark: Do Audio LLMs Leak What They Hear?
por: Wang, Jin, et al.
Publicado: (2026)

DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent
por: Zhu, Pengyu, et al.
Publicado: (2025)

Ada-RS: Adaptive Rejection Sampling for Selective Thinking
por: Ge, Yirou, et al.
Publicado: (2026)

Toward Scalable Verifiable Reward: Proxy State-Based Evaluation for Multi-turn Tool-Calling LLM Agents
por: Chuang, Yun-Shiuan, et al.
Publicado: (2026)

LARFT: Closing the Cognition-Action Gap for Length Instruction Following in Large Language Models
por: Zhang, Wei, et al.
Publicado: (2026)

CORBA: Contagious Recursive Blocking Attacks on Multi-Agent Systems Based on Large Language Models
por: Zhou, Zhenhong, et al.
Publicado: (2025)

A Survey on Trustworthy LLM Agents: Threats and Countermeasures
por: Yu, Miao, et al.
Publicado: (2025)

Automating Personalization: Prompt Optimization for Recommendation Reranking
por: Wang, Chen, et al.
Publicado: (2025)

LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systems
por: Zhang, Yuanhe, et al.
Publicado: (2025)

SMCP: Secure Model Context Protocol
por: Hou, Xinyi, et al.
Publicado: (2026)

Sequential Recommendation via Adaptive Robust Attention with Multi-dimensional Embeddings
por: Pang, Linsey, et al.
Publicado: (2024)

NEMO-4-PAYPAL: Leveraging NVIDIA's Nemo Framework for empowering PayPal's Commerce Agent
por: Garg, Sudhanshu, et al.
Publicado: (2025)

Ev-Trust: An Evolutionarily Stable Trust Mechanism for Decentralized LLM-Based Multi-Agent Service Economies
por: Wang, Jiye, et al.
Publicado: (2025)

Pivoting Retail Supply Chain with Deep Generative Techniques: Taxonomy, Survey and Insights
por: Wang, Yuan, et al.
Publicado: (2024)

Jailbreaking Large Language Diffusion Models: Revealing Hidden Safety Flaws in Diffusion-Based Text Generation
por: Zhang, Yuanhe, et al.
Publicado: (2025)

Design of a Reconfigurable Microfluidic System Enabled by Magnetic Miniature Robots
por: Yuanhe Chen, et al.
Publicado: (2025)

Mesh Memory Protocol: Semantic Infrastructure for Multi-Agent LLM Systems
por: Xu, Hongwei
Publicado: (2026)

SAMEP: A Secure Protocol for Persistent Context Sharing Across AI Agents
por: Masoor, Hari
Publicado: (2025)

Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw
por: Yao, Hongwei, et al.
Publicado: (2026)

MCPXKIT: The Unified Toolkit for Analyzing Model Context Protocol Security
por: Guo, Yongjian, et al.
Publicado: (2025)

SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration
por: Wen, Zhuofan, et al.
Publicado: (2026)

Design and Development of a Trust Mechanism to Enhance Security Protection in SDN‐Based IoT Network
por: Pang‐Wei Tsai, et al.
Publicado: (2025)

AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Models
por: Zhang, Qianchi, et al.
Publicado: (2024)

Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents
por: Maloyan, Narek, et al.
Publicado: (2026)

Model Context Protocol for Vision Systems: Audit, Security, and Protocol Extensions
por: Tiwari, Aditi, et al.
Publicado: (2025)

GAP-Net: Calibrating User Intent via Gated Adaptive Progressive Learning for CTR Prediction
por: Ke, Shenqiang, et al.
Publicado: (2026)

When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning
por: Xu, Ruotao, et al.
Publicado: (2026)

From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agents
por: Wang, Xinyue, et al.
Publicado: (2026)

Lightweight Query Routing for Adaptive RAG: A Baseline Study on RAGRouter-Bench
por: Bansal, Prakhar, et al.
Publicado: (2026)

Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL
por: Luo, Qin-Wen, et al.
Publicado: (2025)

Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
por: Terekhov, Mikhail, et al.
Publicado: (2025)