Data Driven APT Attribution and AI/ML Research
summary
A free desktop app called FIT Adversary Finder uses the MITRE ATT&CK database, Python and a neo4j graph to map observed TTP IDs or names to APT profiles and mitigation steps, returning ranked matches (example shown: 36% match) and relationship graphs; the tool runs and is being released to GitHub. A planned ML layer extracts TTPs from free text and uses federated learning so models—not raw data—are shared; the ML work is proof-of-concept and needs collaborative training data.
AI-written summary · about
chapters (5)
related talks
44mUnmasking APTs: An Automated Approach for Real-World Threat Attribution
38mAdversary Detection Pipelines: Finally Making Your Threat Intel Useful
48mMITRE ATT&CK: The Play at Home Edition
01h 47mMITRE ATT&CK Fundamentals
13mAPTGen: An Approach towards Generating Practical Dataset Labelled with Targeted...
39mThe PR3TACK Initiative: Building the World’s First Preemptive Tactics & Countermeasures Knowledgebas
28mWho Did It? Getting Started with Threat Actor Profiling
26mImproving Cybersecurity Posture with an AI Security Assistant