Metraipolis › archive › dc_db36b4402fe6

When Ambiguity Meets Atypicality: Dual-Perspective Test Input Prioritization for DNNs — arXiv:2609.34703

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34703
License (as archived)
CC0-1.0
Archived
2026-10-07T23:02:14.384Z
SHA-256 of the archived text
95a97e6bc04fbb99d1b1d6579aae760b7ec0311a697540ffc15394ea1faef981
Stable URL of this page
https://metraipolis.com/documento/dc_db36b4402fe6

How to cite

When Ambiguity Meets Atypicality: Dual-Perspective Test Input Prioritization for DNNs — arXiv:2609.34703 — arXiv (en), https://arxiv.org/abs/2609.34703 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db36b4402fe6 (Metraipolis archive dc_db36b4402fe6, sha256 95a97e6bc04fbb99d1b1d6579aae760b7ec0311a697540ffc15394ea1faef981)
BibTeX
@misc{dcdb36b4402fe6,
  title = {When Ambiguity Meets Atypicality: Dual-Perspective Test Input Prioritization for DNNs — arXiv:2609.34703},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34703},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db36b4402fe6; sha256 95a97e6bc04fbb99d1b1d6579aae760b7ec0311a697540ffc15394ea1faef981},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34703. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

While Deep Neural Networks (DNNs) have achieved remarkable progress in cutting-edge domains, their inherent brittleness has become a growing concern. To ensure the reliability and safety of DNN-enabled software, DNN testing has emerged as an indispensable practice. Within this context, test input prioritization is essential for early fault detection and reducing labeling costs. However, it remains challenging to accurately identify failure-inducing inputs. Although decision ambiguity and distributional atypicality are two widely adopted perspectives for characterizing inter-class competition and intra-class typicality respectively, relying on either perspective in isolation inevitably introduces blind spots. In this paper, we propose DuFP (Dual perspective Feature space Prioritization), a KNN density-based test input prioritization approach for DNNs that jointly incorporates both inter-class and intra-class perspectives. The prioritization framework of DuFP is built upon class-conditional density estimation. Based on the estimation results, prediction correctness is characterized by an ambiguity score and an atypicality score, with the former reflecting decision ambiguity and the latter quantifying distributional atypicality. A hybrid uncertainty score is then constructed by integrating both scores to guide the final prioritization. We evaluate DuFP on prioritization and selection tasks across image and text datasets under clean, corrupted, and adversarial scenarios. Experimental results demonstrate that DuFP effectively and efficiently prioritizes fault-inducing inputs and outperforms state-of-the-art approaches.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-29 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.34703 — 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 2026-10-07T22:39:35.212Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).