Metraipolis › archive › dc_aade35d7d324

A Convolutional Layer Activation Dimensionality Reduction for Out-of-Distribution and Adversarial Attack Detection Methods — arXiv:2608.10203

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10203
License (as archived)
CC0-1.0
Archived
2026-10-19T06:30:10.889Z
SHA-256 of the archived text
24fce168d43e10ee579fc8d9f08ae74c2439b07ac5ecd80cfba53682bb656b48
Stable URL of this page
https://metraipolis.com/documento/dc_aade35d7d324

How to cite

A Convolutional Layer Activation Dimensionality Reduction for Out-of-Distribution and Adversarial Attack Detection Methods — arXiv:2608.10203 — arXiv (en), https://arxiv.org/abs/2608.10203 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aade35d7d324 (Metraipolis archive dc_aade35d7d324, sha256 24fce168d43e10ee579fc8d9f08ae74c2439b07ac5ecd80cfba53682bb656b48)
BibTeX
@misc{dcaade35d7d324,
  title = {A Convolutional Layer Activation Dimensionality Reduction for Out-of-Distribution and Adversarial Attack Detection Methods — arXiv:2608.10203},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10203},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aade35d7d324; sha256 24fce168d43e10ee579fc8d9f08ae74c2439b07ac5ecd80cfba53682bb656b48},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10203. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Despite the success of convolutional neural networks in image classification tasks and their general application in multi-modal models, their susceptibility to out-of-distribution and adversarial attack samples raises concerns regarding trustworthiness and safety. Among the approaches to tackle such issues, detection methods that analyze the model's intermediate activations to estimate a confidence score are a promising family that evaluates the decision process, relying on a dimensionality reduction step to enable efficient downstream processing of the high-dimensional activations. However, when considering convolutional layers, the dimensionality reduction methods in the literature either lack a mechanism to control the compression/information-loss trade-off or yield large representations. In this paper, we carefully analyze two state-of-the-art detection methods and their dimensionality reductions for convolutional layers and develop a novel reduction method with a controllable high-compression level. We extend these two state-of-the-art detection methods, enabling the usage of any dimensionality reduction, and evaluate their performance on out-of-distribution and adversarial attack detection. Results show that the detection methods with the proposed dimensionality reduction consistently perform better than, or comparable to, the strongest alternative. Furthermore, the proposed method is shown to reduce computation and memory footprints, given that it has the highest compression among the compared methods.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.10203 — 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 2026-10-19T06:25:27.235Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).