Related papers: Modelling Agent-Skipping Attacks in Message Forwar…
We introduce the concept of continuous transportation task to the context of multi-agent systems. A continuous transportation task is one in which a multi-agent team visits a number of fixed locations, picks up objects, and delivers them to…
Security protocols are building blocks in secure communications. They deploy some security mechanisms to provide certain security services. Security protocols are considered abstract when analyzed, but they can have extra vulnerabilities…
Information exchange is a crucial component of many real-world multi-agent systems. However, the communication between the agents involves two major challenges: the limited bandwidth, and the shared communication medium between the agents,…
This paper presents a new quantum protocol designed to simultaneously transmit information from one source to many recipients. The proposed protocol, which is based on the phenomenon of entanglement, is completely distributed and is…
While the evolution of the Internet was driven by the end-to-end model, it has been challenged by many flavors of middleboxes over the decades. Yet, the basic idea is still fundamental: reliability and security are usually realized…
Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding, code generation, and complex planning. Simultaneously, Multi-Agent Systems (MAS) have garnered attention for their potential to enable…
Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…
We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In the scenarios, we allowed models to autonomously send emails…
Multipath forwarding consists of using multiple paths simultaneously to transport data over the network. While most such techniques require endpoint modifications, we investigate how multipath forwarding can be done inside the network,…
Autonomous agents represent an inevitable evolution of the internet. Current agent frameworks do not embed a standard protocol for agent-to-agent interaction, leaving existing agents isolated from their peers. As intellectual property is…
Message franking is an indispensable abuse mitigation tool for end-to-end encrypted (E2EE) messaging platforms. With it, users who receive harmful content can securely report that content to platform moderators. However, while real-world…
Control-flow hijacking attacks manipulate orchestration mechanisms in multi-agent systems into performing unsafe actions that compromise the system and exfiltrate sensitive information. Recently proposed defenses, such as LlamaFirewall,…
Semantic communications seeks to transfer information from a source while conveying a desired meaning to its destination. We model the transmitter-receiver functionalities as an autoencoder followed by a task classifier that evaluates the…
The Model Context Protocol (MCP) has emerged as a de facto standard for integrating Large Language Models with external tools, yet no formal security analysis of the protocol specification exists. We present the first rigorous security…
Intelligent Cyber-physical systems can be modelled as multi-agent systems with planning capability to impart adaptivity for changing contexts. In such multi-agent systems, the protocol for plan execution must result in the proper completion…
The Stream Control Transmission Protocol (SCTP) is a connection and message oriented transport protocol. It supports multiple uni-directional streams in each direction allowing user message sequence preservation within each stream. This…
Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled powerful autonomous agents capable of complex reasoning and multi-modal tool use. Despite their growing capabilities, today's agent frameworks…
The purpose of this paper is investigating behaviors of Ad Hoc protocols in Agent-based simulation environments. First we bring brief introduction about agents and Ad Hoc networks. We introduce some agent-based simulation tools like NS-2.…
We often assume that agent-to-agent interaction will mirror human conversation. However, agents operate fundamentally differently. What if they could develop communication patterns that are more efficient and better aligned with their…
Goal-oriented communication is a new paradigm that considers the meaning of transmitted information to optimize communication. One possible application is the remote monitoring of a process under communication costs: scheduling updates…