Metraipolis › archive › dc_ec58841da62a

TestifAI: Tomography-Based Testing for Deep Learning Systems — arXiv:2608.18900

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18900
License (as archived)
CC0-1.0
Archived
2026-10-18T13:44:39.896Z
SHA-256 of the archived text
554186454ef1d122cd030b07c4117c7b4d9bc01d2d9f61d10da7423a68475a9d
Stable URL of this page
https://metraipolis.com/documento/dc_ec58841da62a

How to cite

TestifAI: Tomography-Based Testing for Deep Learning Systems — arXiv:2608.18900 — arXiv (en), https://arxiv.org/abs/2608.18900 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec58841da62a (Metraipolis archive dc_ec58841da62a, sha256 554186454ef1d122cd030b07c4117c7b4d9bc01d2d9f61d10da7423a68475a9d)
BibTeX
@misc{dcec58841da62a,
  title = {TestifAI: Tomography-Based Testing for Deep Learning Systems — arXiv:2608.18900},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18900},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec58841da62a; sha256 554186454ef1d122cd030b07c4117c7b4d9bc01d2d9f61d10da7423a68475a9d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18900. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As AI systems are increasingly deployed in safety-critical application domains (e.g., autonomous driving), associated risks increase too. Deep learning models underlying modern AI systems, therefore, must undergo thorough testing to ensure their correct behaviour. A single robustness test involves thousands of inferences to empirically verify if a model's outputs remain stable under a bounded perturbation of its inputs. However, existing testing frameworks lack the means to systematically explore and summarise robustness across a combinatorial space of perturbations. We propose TestifAI, a deep learning testing framework for efficient and accurate estimation of robustness against combinations of perturbations. TestifAI enables users to specify operational conditions as structured spaces of semantic input perturbations (e.g., image blur, brightness and zoom) and discrete severity levels (e.g., low, medium and high). Users can query model robustness for any combination (e.g., "low blur, high brightness, and medium zoom"). To achieve efficiency and accuracy, TestifAI introduces partial model tomography, a novel approach to reconstructing model behaviour in a multi-perturbation space from tests that apply only a small number of perturbations (lower-order projections). To estimate robustness against at least three perturbations, TestifAI trains an auxiliary model on the results of tests involving up to two perturbations only, avoiding execution of an exponential number of tests. Our experiments on five image and language classification tasks show that TestifAI can predict higher-order (3 and 4 perturbations) test outcomes from low-order (1 and 2 perturbations) observations with an aggregate robustness estimation error of less than 7%, while reducing the number of inferences by 60-80%.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.18900 — 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 2026-10-18T13:41:17.886Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).