New Formulation of DNN Statistical Mutation Killing for Ensuring Monotonicity: A Technical Report
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916844632276992 |
|---|---|
| author | Kim, Jinhan Humbatova, Nargiz Jahangirova, Gunel Yoo, Shin Tonella, Paolo |
| author_facet | Kim, Jinhan Humbatova, Nargiz Jahangirova, Gunel Yoo, Shin Tonella, Paolo |
| contents | Mutation testing has emerged as a powerful technique for evaluating the effectiveness of test suites for Deep Neural Networks. Among existing approaches, the statistical mutant killing criterion of DeepCrime has leveraged statistical testing to determine whether a mutant significantly differs from the original model. However, it suffers from a critical limitation: it violates the monotonicity property, meaning that expanding a test set may result in previously killed mutants no longer being classified as killed. In this technical report, we propose a new formulation of statistical mutant killing based on Fisher exact test that preserves the statistical rigour of it while ensuring monotonicity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_11199 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | New Formulation of DNN Statistical Mutation Killing for Ensuring Monotonicity: A Technical Report Kim, Jinhan Humbatova, Nargiz Jahangirova, Gunel Yoo, Shin Tonella, Paolo Software Engineering Mutation testing has emerged as a powerful technique for evaluating the effectiveness of test suites for Deep Neural Networks. Among existing approaches, the statistical mutant killing criterion of DeepCrime has leveraged statistical testing to determine whether a mutant significantly differs from the original model. However, it suffers from a critical limitation: it violates the monotonicity property, meaning that expanding a test set may result in previously killed mutants no longer being classified as killed. In this technical report, we propose a new formulation of statistical mutant killing based on Fisher exact test that preserves the statistical rigour of it while ensuring monotonicity. |
| title | New Formulation of DNN Statistical Mutation Killing for Ensuring Monotonicity: A Technical Report |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2507.11199 |