Metraipolis › archive › dc_2cb2dee98868

Input-Layer Starvation: Why Per-Layer Pruning Breaks IoT Intrusion Detectors — arXiv:2609.30729

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30729
License (as archived)
CC0-1.0
Archived
2026-10-08T02:09:18.621Z
SHA-256 of the archived text
763d79a9763794d776f0b343ab8e0ed37b884fed3728c964f3d17a15278fbb29
Stable URL of this page
https://metraipolis.com/documento/dc_2cb2dee98868

How to cite

Input-Layer Starvation: Why Per-Layer Pruning Breaks IoT Intrusion Detectors — arXiv:2609.30729 — arXiv (en), https://arxiv.org/abs/2609.30729 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2cb2dee98868 (Metraipolis archive dc_2cb2dee98868, sha256 763d79a9763794d776f0b343ab8e0ed37b884fed3728c964f3d17a15278fbb29)
BibTeX
@misc{dc2cb2dee98868,
  title = {Input-Layer Starvation: Why Per-Layer Pruning Breaks IoT Intrusion Detectors — arXiv:2609.30729},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30729},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2cb2dee98868; sha256 763d79a9763794d776f0b343ab8e0ed37b884fed3728c964f3d17a15278fbb29},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30729. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Intrusion detectors for small Internet-of-Things (IoT) devices are usually compressed by pruning and judged by overall accuracy. We show that this hides a severe class-level failure, find its cause, and give low-overhead prevention and repair. On CICIoT2023, a two-layer convolutional detector pruned with uniform layer-wise magnitude pruning at 80% sparsity loses 16 points of accuracy but half of its macro-F1, the mean per-class F1 (0.542 to 0.271 over five independently trained models); 17 of 34 classes are materially damaged. Remaining weight count does not explain it: a perceptron and a transformer pruned to the same or fewer weights lose at most 0.096. The first layer does. It has 192 weights; uniform pruning leaves 38, 46% of its 64 filters lose every input weight, and fine-tuning under that starvation leaves the running means of the first normalisation layer displaced by up to 0.8 standard deviations in a few surviving channels, on which the deployed model collapses. Protecting those 192 weights, or pruning globally at the same sparsity, prevents the collapse (loss 0.013); recomputing the normalisation statistics on unlabelled training data, with no weight changed, repairs it (loss 0.039) and returns the false-alert rate to 33% (dense 29%). Damage shows a strong increasing dose-response in first-layer sparsity, starving a perceptron's input layer reproduces the collapse, and the pattern holds on TON_IoT. The failure is misattribution and false alerts, not silent evasion: on validation-selected blind spots, uniformly pruned detectors misattribute 72% of the traffic, against 50% with the first layer protected and 47% for the dense model.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-28 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.30729 — 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 2026-10-08T01:42:25.527Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).