Latent Regularization in Generative Test Input Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910024671952896 |
|---|---|
| author | Merabishvili, Giorgi Weißl, Oliver Stocco, Andrea |
| author_facet | Merabishvili, Giorgi Weißl, Oliver Stocco, Andrea |
| contents | This study investigates the impact of regularization of latent spaces through truncation on the quality of generated test inputs for deep learning classifiers. We evaluate this effect using style-based GANs, a state-of-the-art generative approach, and assess quality along three dimensions: validity, diversity, and fault detection. We evaluate our approach on the boundary testing of deep learning image classifiers across three datasets, MNIST, Fashion MNIST, and CIFAR-10. We compare two truncation strategies: latent code mixing with binary search optimization and random latent truncation for generative exploration. Our experiments show that the latent code-mixing approach yields a higher fault detection rate than random truncation, while also improving both diversity and validity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_15552 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Latent Regularization in Generative Test Input Generation Merabishvili, Giorgi Weißl, Oliver Stocco, Andrea Software Engineering Machine Learning This study investigates the impact of regularization of latent spaces through truncation on the quality of generated test inputs for deep learning classifiers. We evaluate this effect using style-based GANs, a state-of-the-art generative approach, and assess quality along three dimensions: validity, diversity, and fault detection. We evaluate our approach on the boundary testing of deep learning image classifiers across three datasets, MNIST, Fashion MNIST, and CIFAR-10. We compare two truncation strategies: latent code mixing with binary search optimization and random latent truncation for generative exploration. Our experiments show that the latent code-mixing approach yields a higher fault detection rate than random truncation, while also improving both diversity and validity. |
| title | Latent Regularization in Generative Test Input Generation |
| topic | Software Engineering Machine Learning |
| url | https://arxiv.org/abs/2602.15552 |