Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Nakamura, Mason, Kumar, Abhinav, Mahmud, Saaduddin, Abdelnabi, Sahar, Zilberstein, Shlomo, Bagdasarian, Eugene
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918161680433152
author Nakamura, Mason
Kumar, Abhinav
Mahmud, Saaduddin
Abdelnabi, Sahar
Zilberstein, Shlomo
Bagdasarian, Eugene
author_facet Nakamura, Mason
Kumar, Abhinav
Mahmud, Saaduddin
Abdelnabi, Sahar
Zilberstein, Shlomo
Bagdasarian, Eugene
contents A multi-agent system (MAS) powered by large language models (LLMs) can automate tedious user tasks such as meeting scheduling that requires inter-agent collaboration. LLMs enable nuanced protocols that account for unstructured private data, user constraints, and preferences. However, this design introduces new risks, including misalignment and attacks by malicious parties that compromise agents or steal user data. In this paper, we propose the Terrarium framework for fine-grained study on safety, privacy, and security in LLM-based MAS. We repurpose the blackboard design, an early approach in multi-agent systems, to create a modular, configurable testbed for multi-agent collaboration. We identify key attack vectors such as misalignment, malicious agents, compromised communication, and data poisoning. We implement three collaborative MAS scenarios with four representative attacks to demonstrate the framework's flexibility. By providing tools to rapidly prototype, evaluate, and iterate on defenses and designs, Terrarium aims to accelerate progress toward trustworthy multi-agent systems.
format Preprint
id arxiv_https___arxiv_org_abs_2510_14312
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies
Nakamura, Mason
Kumar, Abhinav
Mahmud, Saaduddin
Abdelnabi, Sahar
Zilberstein, Shlomo
Bagdasarian, Eugene
Artificial Intelligence
Computation and Language
Cryptography and Security
I.2.7; I.2.11
A multi-agent system (MAS) powered by large language models (LLMs) can automate tedious user tasks such as meeting scheduling that requires inter-agent collaboration. LLMs enable nuanced protocols that account for unstructured private data, user constraints, and preferences. However, this design introduces new risks, including misalignment and attacks by malicious parties that compromise agents or steal user data. In this paper, we propose the Terrarium framework for fine-grained study on safety, privacy, and security in LLM-based MAS. We repurpose the blackboard design, an early approach in multi-agent systems, to create a modular, configurable testbed for multi-agent collaboration. We identify key attack vectors such as misalignment, malicious agents, compromised communication, and data poisoning. We implement three collaborative MAS scenarios with four representative attacks to demonstrate the framework's flexibility. By providing tools to rapidly prototype, evaluate, and iterate on defenses and designs, Terrarium aims to accelerate progress toward trustworthy multi-agent systems.
title Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies
topic Artificial Intelligence
Computation and Language
Cryptography and Security
I.2.7; I.2.11
url https://arxiv.org/abs/2510.14312