Metraipolis › archive › dc_8ee5ca9822b9
Robust Representation Learning for Spiking Neural Networks based on Conditional Information Bottleneck — arXiv:2610.28110
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.28110
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-21T07:07:02.179Z
- SHA-256 of the archived text
65e8917a81f1b17e3fbc6ddfdddc42029a85ba70bf540bf4b9bae600288910f8- Stable URL of this page
https://metraipolis.com/documento/dc_8ee5ca9822b9
How to cite
Robust Representation Learning for Spiking Neural Networks based on Conditional Information Bottleneck — arXiv:2610.28110 — arXiv (en), https://arxiv.org/abs/2610.28110 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8ee5ca9822b9 (Metraipolis archive dc_8ee5ca9822b9, sha256 65e8917a81f1b17e3fbc6ddfdddc42029a85ba70bf540bf4b9bae600288910f8)
BibTeX
@misc{dc8ee5ca9822b9,
title = {Robust Representation Learning for Spiking Neural Networks based on Conditional Information Bottleneck — arXiv:2610.28110},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.28110},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8ee5ca9822b9; sha256 65e8917a81f1b17e3fbc6ddfdddc42029a85ba70bf540bf4b9bae600288910f8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.28110. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Spiking Neural Networks (SNNs) have shown great potential for low-power neuromorphic computing due to their event-driven processing and spatiotemporal sparsity, but they remain vulnerable to input perturbations, hardware-intrinsic noise, and adversarial attacks in real-world deployment. We attribute this vulnerability partly to input-specific hidden representations learned by standard SNNs trained with conventional cross-entropy loss, as our information-plane analysis empirically shows that substantial input-related information can still be retained after label-predictive information becomes stable. To address this issue, we propose SCIB, a simple yet effective robust learning objective for SNNs based on the Conditional Information Bottleneck. Different from conventional variational IB methods, SCIB replaces the mutual information compression term $I(X;S)$ with the conditional mutual information $I(X;S|Y)$ and derives a tractable variational upper bound. Moreover, it introduces a learnable class-conditional prior instead of a label-agnostic isotropic Gaussian prior, improving the expressiveness of variational compression and encouraging class-structured representations when combined with the supervised classification objective. Systematic experiments on Fashion-MNIST, CIFAR-10, and CIFAR-100 under external environmental noise, neuromorphic hardware noise, and adversarial attacks show that SCIB improves robustness over standard SNNs and IB-based baselines under most evaluated noise conditions, improves adversarial accuracy under the evaluated attacks without using adversarial training, and reduces the SynOps-based single-sample inference energy consumption by 24.9% relative to an unconstrained SNN baseline. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.28110 — 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 2026-10-21T07:05:43.470Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).