一句话：提出 DuFP：基于 KNN 密度、融合类间歧义与类内非典型性双视角的 DNN 测试输入优先级排序方法。
深度神经网络在关键领域的广泛应用使其脆弱性备受关注，而测试输入优先级排序对于尽早发现故障、降低标注成本至关重要。然而，准确识别故障诱发输入仍然困难：决策歧义与分布非典型性分别刻画类间竞争与类内典型性，但单独使用任一视角都会带来盲区。本文提出 DuFP，一种基于 KNN 密度的测试输入优先级排序方法，同时融合类间与类内视角。其排序框架建立在类条件密度估计之上，据此构造歧义分数（反映决策歧义）与非典型性分数（量化分布非典型性），并整合为混合不确定性分数以指导最终排序。作者在图像和文本数据集上，于干净、损坏与对抗三类场景中评估了优先级排序与选择任务，实验表明 DuFP 能高效有效地优先排序故障诱发输入，并优于现有最先进方法。
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.
@inproceedings{paperbot12221,
title = {When Ambiguity Meets Atypicality: Dual-Perspective Test Input Prioritization for DNNs},
author = {Haoran Li and Shihai Wang and Bin Liu and Jialuo Chen and Wenjing Zhu and Yu Liu and Tengfei Shi and Shudi Guo},
booktitle = {ASE},
year = {2026},
doi = {10.1145/3832783.3834351}
}