Verifiable Manifest Signing and Transparency Enforcement for Secure MCP-Based LLM Pipelines

2026-01-30 · Saeid Jamshidi, Kawser Wazed Nafi, Arghavan Moradi Dakhel, Foutse Khomh, Mohammad Hamdaqa arxiv

Large Language Models (LLMs) are increasingly deployed in tool-driven environments such as healthcare analytics, financial systems, retrieval-augmented generation (RAG), and multi-agent workflows. Although the Model Context Protocol (MCP) standardizes how LLM applications expose and invoke external tools, its baseline model does not require tool-use manifests to be cryptographically authenticated, freshness-checked, policy-bound, or independently auditable before execution. As a result, MCP pipelines may remain vulnerable to manifest tampering, unauthorized tool invocation, replay of stale requests, and weak accountability. This paper presents a manifest-level enforcement layer for MCP-based LLM pipelines. It treats each MCP tool-use manifest as a first-class security object whose canonical form must be policy-validated, freshness-checked, digitally signed, verified before execution, and linked to tamper-evident audit evidence. The framework binds tool invocation to verifiable manifest integrity and fail-closed authorization, separates user-visible request parameters from execution metadata, rejects non-compliant or stale manifests before execution, and records accepted invocations in a Merkle-based transparency log. Evaluation across GPT-5.3, LLaMA-3.5, and DeepSeek-V3 using up to 50,000 manifest instances shows near-linear scalability (R^2 = 0.998), bounded verification latency (<= 9.4 ms on edge devices), and rejection of expired, malformed, replayed, and policy-violating manifests, with rejection rates above 98.7%. Experiments in healthcare, finance, RAG, and multi-agent settings show that manifest-level cryptographic enforcement enables low-overhead, traceable, and auditable execution control for heterogeneous LLM-tool pipelines.

📄 PDF Abstract BibTeX arXiv:2601.23132

Code (0)

등록된 구현이 없습니다.

The Limits of AI Data Transparency Policy: Three Disclosure Fallacies

2026-01-26 · Judy Hanwen Shen, Ken Liu, Angelina Wang, Sarah H. Cen 외 arxiv

Data transparency has emerged as a rallying cry for addressing concerns about AI: data quality, privacy, and copyright chief among them. Yet while these calls are crucial for accountability, current transparency policies…

Autonomous Agents on Blockchains: Standards, Execution Models, and Trust Boundaries

2026-01-08 · Saad Alqithami arxiv

Advances in large language models have enabled agentic AI systems that can reason, plan, and interact with external tools to execute multi-step workflows, while public blockchains have evolved into a programmable substra…

A Privacy-Preserving Cloud Architecture for Distributed Machine Learning at Scale

2025-12-11 · Vinoth Punniyamoorthy, Ashok Gadi Parthi, Mayilsamy Palanigounder, Ravi Kiran Kodali 외 arxiv

Distributed machine learning systems require strong privacy guarantees, verifiable compliance, and scalable deployment across heterogeneous and multi-cloud environments. This work introduces a cloud-native privacy-preser…

Reinforcement Learning Federated Learning

Blockchain-based Secure Client Selection in Federated Learning

2022-05-11 · Truc Nguyen, Phuc Thai, Tre' R. Jeter, Thang N. Dinh 외

Despite the great potential of Federated Learning (FL) in large-scale distributed learning, the current system is still subject to several privacy issues due to the fact that local models trained by clients are exposed t…

Federated Learning

Neuro-Symbolic Compliance: Integrating LLMs and SMT Solvers for Automated Financial Legal Analysis

2026-01-07 · Yung-Shen Hsia, Fang Yu, Jie-Hong Roland Jiang arxiv

Financial regulations are increasingly complex, hindering automated compliance-especially the maintenance of logical consistency with minimal human oversight. We introduce a Neuro-Symbolic Compliance Framework that integ…

Code Generation