Metraipolis › archive › dc_bc560648f294
Testing concept-level audits of melanoma classifiers with diffusion counterfactuals and matched positive controls — arXiv:2611.02119
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02119
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:36:25.008Z
- SHA-256 of the archived text
f0e850d1d609cf273486cf404a96928293b0d1d46f542e4e3870bc9350bd531c- Stable URL of this page
https://metraipolis.com/documento/dc_bc560648f294
How to cite
Testing concept-level audits of melanoma classifiers with diffusion counterfactuals and matched positive controls — arXiv:2611.02119 — arXiv (en), https://arxiv.org/abs/2611.02119 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc560648f294 (Metraipolis archive dc_bc560648f294, sha256 f0e850d1d609cf273486cf404a96928293b0d1d46f542e4e3870bc9350bd531c)
BibTeX
@misc{dcbc560648f294,
title = {Testing concept-level audits of melanoma classifiers with diffusion counterfactuals and matched positive controls — arXiv:2611.02119},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02119},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc560648f294; sha256 f0e850d1d609cf273486cf404a96928293b0d1d46f542e4e3870bc9350bd531c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02119. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Concept-based explanations of melanoma classifiers are rarely tested against controls with known targets. We built a counterfactual audit from a diffusion model conditioned on seven 7-point checklist concepts and tested it with such controls. Colour-calibrated start noise reduced colour outliers from 78.5-84.8\% to 6.6-13.3\%. Four of seven knobs were target-dominant but also changed other concepts. Quartile-based positive controls were confounded, and the audit failed its pre-specified rule. It recovered the targets of all 16 controls matched on the generator's pseudo-labels and of 12 of 12 controls labelled by a second evaluator, for three concepts; concept activation vectors recovered fewer (11 of 16). In 18 permuted-label classifiers, significant sweep responses and target rankings also arose, whereas standardised effect margins separated the controls from these null classifiers. The pigmentation sweep raised the melanoma logit in 15 of 15 ISIC 2020 classifiers (+3.12 on average) and 6 of 6 HAM10000 classifiers (+4.01), about four times the null response in scale-free units; the regression effect did not transfer. An exploratory decomposition, evaluated against the controls, suggested that knob cross-talk partly hides vascular responses. Matched controls and null classifiers are practical checks of concept audits. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.02119 — 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 2026-11-03T10:29:48.843Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).