New AI system ThreatForest automates attack tree generation from code

Researchers have developed ThreatForest, a novel multi-agent system designed to automate threat modeling for cloud-native software development. This system analyzes code repositories to generate structured attack trees, mapping attack steps to adversary tactics, techniques, and procedures (TTPs) from frameworks like MITRE ATT&CK and CAPEC. ThreatForest also synthesizes actionable mitigations and incorporates human-in-the-loop validation points. While the overall system demonstrates promising results in generating threat statements, attack trees, and mitigations, the accuracy of the embedding stage for TTP mapping remains a bottleneck. AI

IMPACT This system could significantly speed up threat modeling for cloud-native applications, freeing up scarce security expertise for more complex tasks.

RANK_REASON The cluster contains an academic paper detailing a new system and its evaluation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• MITRE ATT&CK
• ThreatForest

• paper
• product
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →