Related papers: Simplified and Secure MCP Gateways for Enterprise …
Recent changes in standards and regulations, driven by the increasing importance of software systems in meeting societal needs, mandate increased security testing of software systems. Penetration testing has been shown to be a reliable…
Human-AI collaboration faces growing challenges as AI systems increasingly outperform humans on complex tasks, while humans remain responsible for orchestration, validation, and decision oversight. To address this imbalance, we introduce…
Mobile Edge Computing (MEC) is a new computing paradigm that enables cloud computing and information technology (IT) services to be delivered at the network's edge. By shifting the load of cloud computing to individual local servers, MEC…
With the rise of LLMs, a large number of Model Context Protocol (MCP) services have emerged since the end of 2024. However, the effectiveness and efficiency of MCP servers have not been well studied. To study these questions, we propose an…
Multi-path TCP (MP-TCP) has the potential to greatly improve application performance by using multiple paths transparently. We propose a fluid model for a large class of MP-TCP algorithms and identify design criteria that guarantee the…
The integration of AI into modern critical infrastructure systems, such as healthcare, has introduced new vulnerabilities that can significantly impact workflow, efficiency, and safety. Additionally, the increased connectivity has made…
Existing agent communication frameworks face critical limitations in providing verifiable audit trails without compromising the privacy and confidentiality of agent interactions. The protection of agent communication privacy while ensuring…
The Model Context Protocol (MCP) is rapidly emerging as the middleware for LLM-based applications, offering a standardized interface for tool integration. However, its built-in security mechanisms are minimal: while schemas and declarations…
Large Language Models (LLMs) remain static in functionality after training, and extending their capabilities requires integration with external data, computation, and services. The Model Context Protocol (MCP) has emerged as a standard…
Autonomous AI agents powered by large language models are being deployed in production with capabilities including shell execution, file system access, database queries, and multi-party communication. Recent red teaming research…
Standard protocols such as the Model Context Protocol (MCP) that allow LLMs to connect to tools have recently boosted "agentic" AI applications, which, powered by LLMs' planning capabilities, promise to solve complex tasks with the access…
Multi-agent systems (MAS) powered by LLMs promise adaptive, reasoning-driven enterprise workflows, yet granting agents autonomous control over tools, memory, and communication introduces attack surfaces absent from deterministic pipelines.…
In many scenarios, such as emergency response or ad hoc collaboration, it is critical to reduce the overhead in integrating data. Ideally, one could perform the entire process interactively under one unified interface: defining extractors…
The rise of generative AI (GenAI) multi-agent systems (MAS) necessitates standardized protocols enabling agents to discover and interact with external tools. However, these protocols introduce new security challenges, particularly; tool…
Large Language Model (LLM) agents increasingly interact with external systems through tool-calling protocols such as the Model Context Protocol (MCP). In prevailing architectures, the agent must reason about every tool invocation in every…
The integration of Large Language Models (LLMs) into network operations (AIOps) is hindered by two fundamental challenges: the stochastic grounding problem, where LLMs struggle to reliably parse unstructured, vendor-specific CLI output, and…
Enterprise adoption of cloud-based AI agents faces a fundamental privacy dilemma: leveraging powerful cloud models requires sharing sensitive data, while local processing limits capability. Current agent frameworks like MCP and A2A assume…
Explicit modeling of capabilities and skills -- whether based on ontologies, Asset Administration Shells, or other technologies -- requires considerable manual effort and often results in representations that are not easily accessible to…
Modern AI agents routinely depend on secrets such as API keys and SSH credentials, yet the dominant deployment model still exposes those secrets directly to the agent process through environment variables, local files, or forwarding…
This white paper presents an analysis done by the MAMI project of the privacy and security concerns surrounding middlebox cooperation protocols (MCPs), based on our experimental experience with the Path Layer UDP Substrate (PLUS) proposal.…