一句话：提出黑盒方法 CIT4DNN，将组合交互测试用于生成模型潜在空间，生成特征多样且稀有的 DNN 测试输入。
深度神经网络已用于安全关键系统，但现有测试生成方法难以系统覆盖输入数据分布，且未探究稀有输入与故障的关系。本文提出 CIT4DNN，一种自动化黑盒方法：将组合交互测试应用于生成模型的潜在空间以构造特征多样的测试集，并通过对潜在空间几何施加约束来生成稀有且能暴露故障的测试输入。作者在多个数据集和模型上评估，结果表明 CIT4DNN 生成的测试比当前最优方法具有更高的特征多样性，并能更有效地针对稀有故障暴露输入。
Deep neural networks (DNN) are being used in a wide range of applications including safety-critical systems. Several DNN test generation approaches have been proposed to generate fault-revealing test inputs. However, the existing test generation approaches do not systematically cover the input data distribution to test DNNs with diverse inputs, and none of the approaches investigate the relationship between rare inputs and faults. We propose cit4dnn, an automated black-box approach to generate DNN test sets that are feature-diverse and that comprise rare inputs. cit4dnn constructs diverse test sets by applying combinatorial interaction testing to the latent space of generative models and formulates constraints over the geometry of the latent space to generate rare and fault-revealing test inputs. Evaluation on a range of datasets and models shows that cit4dnn generated tests are more feature diverse than the state-of-the-art, and can target rare fault-revealing testing inputs more effectively than existing methods.
@inproceedings{paperbot11480,
title = {CIT4DNN: Generating Diverse and Rare Inputs for Neural Networks Using Latent Space Combinatorial Testing},
author = {Swaroopa Dola and Rory McDaniel and Matthew B. Dwyer and Mary Lou Soffa},
booktitle = {ICSE},
year = {2024},
doi = {10.1145/3597503.3639106}
}