Metraipolis › archive › dc_ff6154182f0d

Stress-Testing Structure-Aware Calibration of Malware Graph Neural Networks under Type Shift — arXiv:2609.28517

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.28517
License (as archived)
CC0-1.0
Archived
2026-10-08T04:53:14.362Z
SHA-256 of the archived text
88e0a8f7cae64f69b9f55077b9136c0d550793ec45a4083942fe2b4d4da02519
Stable URL of this page
https://metraipolis.com/documento/dc_ff6154182f0d

How to cite

Stress-Testing Structure-Aware Calibration of Malware Graph Neural Networks under Type Shift — arXiv:2609.28517 — arXiv (en), https://arxiv.org/abs/2609.28517 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff6154182f0d (Metraipolis archive dc_ff6154182f0d, sha256 88e0a8f7cae64f69b9f55077b9136c0d550793ec45a4083942fe2b4d4da02519)
BibTeX
@misc{dcff6154182f0d,
  title = {Stress-Testing Structure-Aware Calibration of Malware Graph Neural Networks under Type Shift — arXiv:2609.28517},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28517},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff6154182f0d; sha256 88e0a8f7cae64f69b9f55077b9136c0d550793ec45a4083942fe2b4d4da02519},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28517. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Post-hoc malware calibrators can condition confidence on graph structure, but their structural inputs may leave the support represented by validation data under malware-type shift. We study this risk on MalNet-Tiny by holding out each of four malware types across three seeds, freezing a graph isomorphism network, and fitting post-hoc mappings only on known-type data. Adding eight community covariates to a generic-topology calibrator increases mean negative log likelihood (NLL) by 0.1369; a type-cluster bootstrap gives a 95% interval of [-0.0125, 0.2864]. A capacity-matched control adds eight label-independent nuisance variables over 20 deterministic repeats and increases NLL by only 0.0415, indicating that input count explains part but not all of the degradation. We then use calibration data to define a community-support guard: predictions outside the 95th percentile of calibration-standardized community displacement revert to the generic calibrator. The guard reduces combined NLL by 0.1133 and high-confidence errors from 43.25 to 33.25 per 400-sample cell, while its NLL remains close to the generic baseline. These results show how structural covariates can create support-sensitive confidence errors and how a label-free fallback can recover most of the resulting loss.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.28517 — 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 2026-10-08T04:30:43.781Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).