DUPIN: Attack Learning Is Still Needed! Demonstrating Few-Shot after Unsupervised Pretraining Is A Nimble Forensics Learner
DUPIN pairs unsupervised pretraining on provenance graphs with few-shot learning, enabling attack forensics with minimal labelled data — a potential accelerator for under-resourced SOCs.
Summary written by editorial AI · Source link below
arXiv:2609.00259v1 Announce Type: new Abstract: We propose a novel approach to learning-based attack forensics called DUPIN. DUPIN performs unsupervised pre-training on an enormous amount of audit events in the form of provenance graphs. It then proceeds to a few-shot learning stage, leveraging a small number of labeled attack examples to fine-tune its detection capabilities. We pretrain DUPIN on up to 38 - 52 days of audit logs (7.3TB total) and evaluate it against various baselines on 25 APT
Editorial Analysis
Enterprises struggling with labelled-data scarcity for threat detection could benefit from forensic models that learn attack patterns from a handful of examples.
Forward-looking interpretation drafted by editorial AI under human review — not a reproduction of the source. See methodology.
External link — opens at arXiv Crypto & Security in a new tab.
More from the Research Desk
- 39 New Methods That Compromise Passkey Authentication3d
- Security Vulnerability in a Voting System3d
- Selfie-Capture Dynamics as an Auxiliary Signal Against Deepfakes and Injection Attacks for Mobile Identity Verification4d
- How Reliable Is the Multi-Input Heuristic for Bitcoin Address Clustering in Law Enforcement Contexts?4d
- Privacy Leakage in Federated Learning: Gradient-Based Client Identity Inference and Defenses for Inertial Sensing in Vehicular Edge Networks4d