Cover Image

Semantic Attacks on Tool-Augmented LLMs: Securing the Model Context Protocol Against Descriptor-Level Manipulation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jamshidi, Saeid, Dakhel, Arghavan Moradi, Nafi, Kawser Wazed, Khomh, Foutse
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Secure Tool Manifest and Digital Signing Solution for Verifiable MCP and LLM Pipelines
by: Jamshidi, Saeid, et al.
Published: (2026)

Self-Adaptive Multi-Agent LLM-Based Security Pattern Selection for IoT Systems
by: Jamshidi, Saeid, et al.
Published: (2026)

Tri-LLM Cooperative Federated Zero-Shot Intrusion Detection with Semantic Disagreement and Trust-Aware Aggregation
by: Jamshidi, Saeid, et al.
Published: (2026)

Leveraging Machine Learning Techniques in Intrusion Detection Systems for Internet of Things
by: Jamshidi, Saeid, et al.
Published: (2025)

Application of Deep Reinforcement Learning for Intrusion Detection in Internet of Things: A Systematic Review
by: Jamshidi, Saeid, et al.
Published: (2025)

Think Fast: Real-Time IoT Intrusion Reasoning Using IDS and LLMs at the Edge Gateway
by: Jamshidi, Saeid, et al.
Published: (2025)

The Moral Consistency Pipeline: Continuous Ethical Evaluation for Large Language Models
by: Jamshidi, Saeid, et al.
Published: (2025)

Carbon-Aware Intrusion Detection: A Comparative Study of Supervised and Unsupervised DRL for Sustainable IoT Edge Gateways
by: Jamshidi, Saeid, et al.
Published: (2025)

Adversarial Moral Stress Testing of Large Language Models
by: Jamshidi, Saeid, et al.
Published: (2026)

Evaluating Machine Learning-Driven Intrusion Detection Systems in IoT: Performance and Energy Consumption
by: Jamshidi, Saeid, et al.
Published: (2025)

Energy-Efficient Multi-LLM Reasoning for Binary-Free Zero-Day Detection in IoT Firmware
by: Jamshidi, Saeid, et al.
Published: (2025)

Multi-Agent LLM Governance for Safe Two-Timescale Reinforcement Learning in SDN-IoT Defense
by: Jamshidi, Saeid, et al.
Published: (2026)

Lightweight Autoencoder-Isolation Forest Anomaly Detection for Green IoT Edge Gateways
by: Jamshidi, Saeid, et al.
Published: (2025)

MPMA: Preference Manipulation Attack Against Model Context Protocol
by: Wang, Zihan, et al.
Published: (2025)

Exploring Security Practices in Infrastructure as Code: An Empirical Study
by: Verdet, Alexandre, et al.
Published: (2023)

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

SMCP: Secure Model Context Protocol
by: Hou, Xinyi, et al.
Published: (2026)

Chain of Targeted Verification Questions to Improve the Reliability of Code Generated by LLMs
by: Ngassom, Sylvain Kouemo, et al.
Published: (2024)

Enhancing IoT Security Against DDoS Attacks through Federated Learning
by: Shirvani, Ghazaleh, et al.
Published: (2024)

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

Securing the Model Context Protocol (MCP): Risks, Controls, and Governance
by: Errico, Herman, et al.
Published: (2025)

3S-Attack: Spatial, Spectral and Semantic Invisible Backdoor Attack Against DNN Models
by: Yin, Jianyao, et al.
Published: (2025)

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

Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs
by: Xiang, Shiyu, et al.
Published: (2025)

Securing Unbounded Differential Privacy Against Timing Attacks
by: Ratliff, Zachary, et al.
Published: (2025)

Temporal Context Awareness: A Defense Framework Against Multi-turn Manipulation Attacks on Large Language Models
by: Kulkarni, Prashant, et al.
Published: (2025)

Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol (MCP) Ecosystem
by: Song, Hao, et al.
Published: (2025)

A Large-Scale Evolvable Dataset for Model Context Protocol Ecosystem and Security Analysis
by: Lin, Zhiwei, et al.
Published: (2025)

Fine-grained Manipulation Attacks to Local Differential Privacy Protocols for Data Streams
by: Li, Xinyu, et al.
Published: (2025)

SecPLF: Secure Protocols for Loanable Funds against Oracle Manipulation Attacks
by: Arora, Sanidhay, et al.
Published: (2024)

Defending Against Attack on the Cloned: In-Band Active Man-in-the-Middle Detection for the Signal Protocol
by: Teng, Wil Liam, et al.
Published: (2024)

SoK: Evaluating 5G Protocols Against Legacy and Emerging Privacy and Security Attacks
by: Eleftherakis, Stavros, et al.
Published: (2024)

Systematization of Knowledge: Security and Safety in the Model Context Protocol Ecosystem
by: Gaire, Shiva, et al.
Published: (2025)

NeuroStrike: Neuron-Level Attacks on Aligned LLMs
by: Wu, Lichao, et al.
Published: (2025)

MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits
by: Radosevich, Brandon, et al.
Published: (2025)

Federated Learning: Attacks, Defenses, Opportunities, and Challenges
by: Shirvani, Ghazaleh, et al.
Published: (2024)

Membership Inference Attacks Against In-Context Learning
by: Wen, Rui, et al.
Published: (2024)

Multi-Agent Framework for Threat Mitigation and Resilience in AI-Based Systems
by: Foundjem, Armstrong, et al.
Published: (2025)

Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks
by: Xiang, Chong, et al.
Published: (2026)

A First Look at the Security Issues in the Model Context Protocol Ecosystem
by: Li, Xiaofan, et al.
Published: (2025)