Metraipolis › archive › dc_864c5d2b6000
Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection — arXiv:2609.16462
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.16462
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T19:33:09.706Z
- SHA-256 of the archived text
4568f906294cae39ab8a945d6d48c2741e8e54b545b939e83fa8573d3a33148d- Stable URL of this page
https://metraipolis.com/documento/dc_864c5d2b6000
How to cite
Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection — arXiv:2609.16462 — arXiv (en), https://arxiv.org/abs/2609.16462 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_864c5d2b6000 (Metraipolis archive dc_864c5d2b6000, sha256 4568f906294cae39ab8a945d6d48c2741e8e54b545b939e83fa8573d3a33148d)
BibTeX
@misc{dc864c5d2b6000,
title = {Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection — arXiv:2609.16462},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.16462},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_864c5d2b6000; sha256 4568f906294cae39ab8a945d6d48c2741e8e54b545b939e83fa8573d3a33148d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16462. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 $41\times$.
Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-16 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.16462 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T18:42:42.614Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).