AURA: A Multi-Agent Intelligence Framework for Knowledge-Enhanced Cyber Threat Attribution
On the map: Retrieval-augmented generation → Privacy and security of RAG
also in 1 more
Abstract (arXiv)
Effective attribution of Advanced Persistent Threats (APTs) increasingly hinges on the ability to correlate behavioral patterns and reason over complex, varied threat intelligence artifacts. We present AURA (Attribution Using Retrieval-Augmented Agents), a multi-agent, knowledge-enhanced framework for automated and interpretable APT attribution. AURA ingests diverse threat data including Tactics, Techniques, and Procedures (TTPs), Indicators of Compromise (IoCs), malware details, adversarial tools, and temporal information, which are processed through a network of collaborative agents. These agents are designed for intelligent query rewriting, context-enriched retrieval from structured threat knowledge bases, and natural language justification of attribution decisions. By combining Retrieval-Augmented Generation (RAG) with Large Language Models (LLMs), AURA enables contextual linking of threat behaviors to known APT groups and supports traceable reasoning across multiple attack phases. Experiments on recent APT campaigns demonstrate AURA's high attribution consistency, expert-aligned justifications, and scalability. This work establishes AURA as a promising direction for advancing transparent, data-driven, and scalable threat attribution using multi-agent intelligence.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 12 of its 35 references that are in the map. First posted on arXiv 11 Jun 2025.
Builds on
12 of 35 references.
References · 12
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
- 2021Evaluating Large Language Models Trained on Codecited by 8,320
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
- 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
- 2024A Survey on LLM-as-a-Judgecited by 1,423
- 2019SPoC: Search-based Pseudocode to Codecited by 176
- 2024TTPXHunter: Actionable Threat Intelligence Extraction as TTPs from Finished Cyber Threat Reportscited by 7
- 2017DeepAPT: Nation-State APT Attribution Using End-to-End Deep Neural Networkscited by 6
- 2025Towards Effective Identification of Attack Techniques in Cyber Threat Intelligence Reports using Large Language Modelscited by 5
- 2025MaLAware: Automating the Comprehension of Malicious Software Behaviours using Large Language Models (LLMs)cited by 4
- 2025On Technique Identification and Threat-Actor Attribution using LLMs and Embedding Modelscited by 2
- 2024Chasing the Shadows: TTPs in Action to Attribute Advanced Persistent Threatscited by 1
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.
Similar, not cited
Close in wording, no citation either way
- 2026CTIFoundry: An Agent-Native Corpus Scaffold for Cyber Threat Intelligence
- 2026Beyond RAG for Cyber Threat Intelligence: A Systematic Evaluation of Graph-Based and Agentic Retrieval
- 2025AutoBnB-RAG: Enhancing Multi-Agent Incident Response with Retrieval-Augmented Generation
- 2026Hierarchical Retrieval Augmented Generation for Adversarial Technique Annotation in Cyber Threat Intelligence Text
- 2026CyberClear: A Benchmark for LLM Agent Systems on APT Attack Chain Provenance
- 2025CTIConnect: A Benchmark for Retrieval-Augmented LLMs over Heterogeneous Cyber Threat Intelligence
- 2026Merging Cyber Threat Intelligence Through Retrieval-Augmented Generation and Small Language Models for Rich Threat Representation
- 2026TACTIC-KG: Toward Small Agent Teams for Cyber Threat Intelligence Knowledge Graph Construction