Metraipolis › archive › dc_dee416c6ffed
Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations — arXiv:2609.38625
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38625
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:44:01.404Z
- SHA-256 of the archived text
339eb8bbd7b4c559378dfd2a37df7864f3f4fda2cffe9666dc51d007316d083a- Stable URL of this page
https://metraipolis.com/documento/dc_dee416c6ffed
How to cite
Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations — arXiv:2609.38625 — arXiv (en), https://arxiv.org/abs/2609.38625 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dee416c6ffed (Metraipolis archive dc_dee416c6ffed, sha256 339eb8bbd7b4c559378dfd2a37df7864f3f4fda2cffe9666dc51d007316d083a)
BibTeX
@misc{dcdee416c6ffed,
title = {Interpretable but Fragile? Robustness of Concept Bottlenecks under Geometric-Semantic Perturbations — arXiv:2609.38625},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38625},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dee416c6ffed; sha256 339eb8bbd7b4c559378dfd2a37df7864f3f4fda2cffe9666dc51d007316d083a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38625. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Concept Bottleneck Models (CBMs) are designed to provide interpretable intermediate representations, yet how such bottlenecks affect robustness remains unclear, with existing studies reporting mixed and sometimes contradictory findings. We argue that these discrepancies arise from conflating different robustness notions and perturbation regimes, rather than from fundamental disagreements about CBMs themselves. To disentangle these factors, we introduce a generator-based evaluation framework that enables controlled comparisons between standard classifiers and CBMs under two distinct perturbation types: continuous geometric perturbations in latent space and discrete semantic interventions in concept space. Within this framework, we evaluate robustness both empirically, via prediction and concept-level sensitivity metrics, and certifiably, using randomized smoothing in latent and concept spaces. Across experiments, we reconcile previously conflicting findings by clarifying when, and in what sense, concept bottlenecks do or do not improve robustness. By further analyzing robustness under varying task conditions, including class semantic similarity and concept vocabulary size, we show that interpretability does not inherently confer robustness. Instead, concept bottlenecks shift where and how sensitivity manifests, revealing a nuanced interpretability robustness trade off that depends critically on the perturbation regime and task structure. Together, our results show that interpretability and robustness are distinct objectives: interpretable intermediate representations do not uniformly improve robustness, but instead redistribute sensitivity across perturbation spaces and model families. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.38625 — 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 2026-10-07T12:14:13.911Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).