NDSS

Unicorn: Runtime Provenance-Based Detector for Advanced Persistent Threats

Xueyuan Han (Harvard University), Thomas Pasquier (University of Bristol), Adam Bates (University of Illinois at Urbana-Champaign), James Mickens (Harvard University), Margo Seltzer (University of British Columbia)

Advanced Persistent Threats (APT) are difficult to detect
due to their ``low-and-slow'' attack patterns and frequent use of zero-day exploits.
We present Babar,
an anomaly-based APT detector that effectively leverages data provenance analysis.
From modeling to detection,
Babar tailors its design specifically for the unique characteristics of APTs.
Through extensive yet time-efficient graph analysis,
Babar explores provenance graphs that provide rich contextual and historical information
to identify stealthy anomalous activities without pre-defined attack signatures.
Using a graph sketching technique,
it summarizes long-running system execution with space efficiency
to combat slow-acting attacks that take place over a long time span.
Babar further improves its detection capability
using a novel modeling approach to understand long-term behavior as the system evolves.
Our evaluation shows that Babar
outperforms an existing state-of-the-art APT detection system
and detects real-life APT scenarios with high accuracy.