ATAG: AI-Agent Application Threat Assessment with Attack Graphs
Open Access
- 4 June 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 805-819
Abstract
Evaluating the security of multi-agent systems (MASs) powered by large language models (LLMs) is challenging, primarily because of the systems' complex internal dynamics and the evolving nature of LLM vulnerabilities. Traditional attack graph (AG) methods often lack the specific capabilities to model attacks on LLMs. This paper introduces AI-agent application Threat assessment with Attack Graphs (ATAG), a novel framework designed to systematically analyze the security risks associated with AI-agent applications. ATAG extends the MulVAL logic-based AG generation tool with custom facts and interaction rules to accurately represent AI-agent topologies, vulnerabilities, and attack scenarios. As part of this research, we also created the LLM vulnerability database (LVD) to initiate the process of standardizing LLM vulnerabilities documentation. To demonstrate ATAG's efficacy, we applied it to three multi-agent applications. Our case studies demonstrated the framework's ability to model and generate AGs for sophisticated, multi-step attack scenarios exploiting vulnerabilities such as prompt injection, excessive agency, sensitive information disclosure, and insecure output handling across interconnected agents. ATAG is an important step toward a robust methodology and toolset to help understand, visualize, and prioritize complex attack paths in multi-agent AI systems (MAASs). It facilitates proactive identification and mitigation of AI-agent threats in multi-agent applications.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Pyopneumothorax tuberculeuxRevue des Maladies Respiratoires Actualités, 2025
- CORAL: Container Online Risk Assessment with Logical attack graphsComputers & Security, 2024
- A survey on large language model based autonomous agentsFrontiers of Computer Science, 2024
- Prioritizing vulnerability patches in large networksExpert Systems with Applications, 2022
- Automatic analysis of attack graphs for risk mitigation and prioritization on large-scale and complex networks in Industry 4.0International Journal of Information Security, 2021
- A survey on the usability and practical applications of Graphical Security ModelsComputer Science Review, 2017
- Computer-Aided Human Centric Cyber Situation AwarenessLecture Notes in Computer Science, 2017
- Causal knowledge analysis for detecting and modeling multi‐step attacksSecurity and Communication Networks, 2016
- Inferring the Stealthy Bridges Between Enterprise Network Islands in Cloud Using Cross-Layer Bayesian Networks2015
- Quantitative Security Risk Assessment of Enterprise Networks2011