Metraipolis › archive › dc_c01fab648d89

Windows Malware Detector as a Compound AI System: Trade-Offs in Accuracy, Efficiency, and Adversarial Robustness — arXiv:2609.08394

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.08394
License (as archived)
CC0-1.0
Archived
2026-10-16T13:40:35.698Z
SHA-256 of the archived text
0a1d945070c4e91b98b998e5605b9975775a0d69d077759a3782acb4629a6a4c
Stable URL of this page
https://metraipolis.com/documento/dc_c01fab648d89

How to cite

Windows Malware Detector as a Compound AI System: Trade-Offs in Accuracy, Efficiency, and Adversarial Robustness — arXiv:2609.08394 — arXiv (en), https://arxiv.org/abs/2609.08394 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c01fab648d89 (Metraipolis archive dc_c01fab648d89, sha256 0a1d945070c4e91b98b998e5605b9975775a0d69d077759a3782acb4629a6a4c)
BibTeX
@misc{dcc01fab648d89,
  title = {Windows Malware Detector as a Compound AI System: Trade-Offs in Accuracy, Efficiency, and Adversarial Robustness — arXiv:2609.08394},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.08394},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c01fab648d89; sha256 0a1d945070c4e91b98b998e5605b9975775a0d69d077759a3782acb4629a6a4c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08394. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Industrial Windows malware detectors are commonly described as Compound AI Systems composed of multiple heterogeneous components, including rule-based mechanisms as well as machine-learning-based static and dynamic analyses. However, due to industrial secrecy and limited public disclosure, the internal architectures of these systems can only be inferred, rendering systematic evaluations of detection accuracy, computational costs, and adversarial robustness largely infeasible. In contrast, academic research provides reproducible and transparent evaluation methodologies, but typically investigates individual detection components in isolation. To bridge the gap between academic research and industrial practice, and inspired by state-of-the-art industrial architectures for Windows malware detection, we propose a novel methodology that (i) explicitly balances the trade-off among detection performance, computational requirements, and robustness, and introduces (ii) system-level threat models that capture how attackers exploit different degrees of knowledge to evade the entire Compound AI System rather than isolated detectors. Experiments conducted on real-world data demonstrate that the Compound AI System training time can be reduced and responsiveness improved while incurring only a marginal loss in detection performance. Leveraging our threat modeling, we show that increasingly knowledgeable attackers craft more effective adversarial examples, revealing the system's strengths and weaknesses, degrading its responsiveness, and exposing a direct trade-off between efficiency and robustness. Finally, we translate these trade-offs into take-home messages and deployment guidelines, helping practitioners to select the system that best matches their operational constraints.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.08394 — 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 2026-10-16T13:09:48.501Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).