Skip to content

Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection

Sep 2026 · arXiv.org · Vol abs/2609.16462 · 0 citations · 23 references
Computer Science

TL;DR

RECAL is presented, an unsupervised framework using relation-balanced masked graph learning to better capture rare interaction patterns and calibrates reconstruction errors against each relation's benign error distribution to produce comparable anomaly evidence, helping distinguish attacks from benign behavior and reduce false alarms.

Abstract

Provenance-Based Intrusion Detection Systems (PIDSs) detect Advanced Persistent Threats (APTs) by analyzing system interactions. However, existing methods largely treat relations uniformly, overlooking statistical heterogeneity; in CADETS, relation frequencies differ by approximately $140{,}000\times$. This may cause PIDSs to focus more on frequent relations and overlook differences in normal error levels across relations, increasing the risk of false alarms and missed detections. We present RECAL, an unsupervised framework using relation-balanced masked graph learning to better capture rare interaction patterns. It further calibrates reconstruction errors against each relation's benign error distribution to produce comparable anomaly evidence, helping distinguish attacks from benign behavior and reduce false alarms. On three DARPA E3 datasets, RECAL achieves F1 scores of 99.99\%, 99.93\%, and 99.99\%, outperforming the best baseline on each dataset by 0.88, 0.82, and 0.42 percentage points, respectively. Compared with the baseline reporting the lowest FPR, RECAL reduces mean FPR by approximately $105\times$, $4\times$, and $41\times$.

View source

Similar papers

Open access 2026

Reducing False Positives in Provenance-Based Intrusion Detection Systems

Provenance-based Intrusion Detection Systems (PIDSes) have been widely used to detect Advanced Persistent Threats (APTs). The PIDSes typically construct provenance graphs based on system logs, learn patterns of benign processes from the provenance graphs, and identify processes whose patterns deviate from benign ones a...

Yue Xiao, Xiao-Li Zhang, Pei-Yang Li et al. · 0 citations
Sep 2026

Where the Numbers Come From: Auditing Evaluation in Provenance-Based Intrusion Detection

This work audit nine released implementations of provenance-based intrusion detectors, execute four detectors using their own code, and isolate three measurement effects that qualify claims from the inspected implementations about alarm precision, performance magnitude and static-attribute sufficiency.

Jih-Wan Moon, Gunhee Kim, Myeongjang Pyeon · 0 citations
Preprint Aug 2026

Provenance, Not Behaviour: A Serialisation Artifact in Edge-IIoTset and a Leakage-Free Benchmark for Precision-Agriculture Intrusion Detection

Edge-IIoTset is the reference benchmark for machine-learning intrusion detection in the industrial Internet of Things, and results reported on it cluster above 99%. We show that much of that performance is not intrusion detection. The preprocessing recipe distributed with the dataset instructs researchers to one-hot en...

M. Galal · 0 citations
Open access Sep 2026

Flow Exporter Provenance as a Major Confounder in Cross-Dataset IoT Intrusion Detection

Machine-learning intrusion detection for the Internet of Things (IoT) routinely exceeds 99% accuracy on single datasets but fails when transferred to new networks or flow exporters. We formalize five failure modes, define a 23-feature canonical schema, and adapt three datasets (CICIoT2023, TON_IoT, Bot-IoT) to build a...

M. Rassam, Mahfoudh Alasaly · 0 citations
Open access 2026

CrossHound: Multi-Source Provenance Correlation for Advanced Persistent Threat Detection and Investigation

Advanced Persistent Threat (APT) attacks pose severe cybersecurity challenges due to their stealthy, prolonged, and highly targeted nature. Despite advancements in defensive technologies, detecting APTs remains difficult because their attack traces are often scattered across multiple data sources, leading to fragmented...

Jia-Ping Gui, Yi-Xin Zhou, Xiang-Geng Zhu et al. · 0 citations
Preprint Aug 2026

Amortised Post-Hoc Explanation with Exact Preservation for Dynamic Graph Anomaly Detectors

X-StrGNN is presented, a post-hoc explanation layer that wraps a trained, frozen StrGNN and emits, for every flagged edge, dual attributions: a structural attribution identifying which contextual interactions in the enclosing subgraph drove the decision, and a temporal attribution identifying which historical snapshot...

Iyad Assaad Nekka, H. Seba, Walid Khaled Hidouci et al. · 0 citations

Related blog posts

Microsoft Research Blog Nov 3, 2026

Learn the rules: The hacker mindset

Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.