Metraipolis › archive › dc_ff1587411bba
Adversarial robustness does not entail human-aligned categorization — arXiv:2611.00715
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00715
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:40:04.939Z
- SHA-256 of the archived text
203583b462dd161502bcd1690195157307a37df08f8994f6fa274d32c99b2981- Stable URL of this page
https://metraipolis.com/documento/dc_ff1587411bba
How to cite
Adversarial robustness does not entail human-aligned categorization — arXiv:2611.00715 — arXiv (en), https://arxiv.org/abs/2611.00715 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff1587411bba (Metraipolis archive dc_ff1587411bba, sha256 203583b462dd161502bcd1690195157307a37df08f8994f6fa274d32c99b2981)
BibTeX
@misc{dcff1587411bba,
title = {Adversarial robustness does not entail human-aligned categorization — arXiv:2611.00715},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00715},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff1587411bba; sha256 203583b462dd161502bcd1690195157307a37df08f8994f6fa274d32c99b2981},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00715. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Adversarial training can improve some forms of correspondence between artificial and biological vision, but whether robust classifiers acquire human-aligned classification behavior remains unclear. We generated 1,008 controversial stimuli by optimizing latent inputs to a pretrained GAN to elicit high-confidence disagreements between pairs of robust ImageNet classifiers. We compared four adversarially robust ImageNet classifiers - ResNet-101, ViT-B, ConvNeXt-L, and Swin-L - with two-alternative category judgments from 60 participants. We first evaluated each classifier on stimuli optimized to elicit disagreement with another model. Across classifiers, accuracy in predicting individual participants' single-trial category choices was near chance (48.6-51.3%), whereas majority judgments from other participants predicted responses with 85.0-86.8% accuracy. An analysis incorporating model prediction strength and participants' reported confidence found weak positive model-human correspondence for the two convolutional models. On stimuli optimized for disagreement between other model pairs, all four robust classifiers predicted human responses above chance but less accurately than predictions based on other participants' majority judgments; the same pattern held for 17 additional RobustBench models not used in stimulus generation. Across these 17 models, mean model-participant agreement was 67.3%, versus 81.3% mean participant-participant agreement on the same images. These results identify model-specific failures of human alignment and a model-human mismatch that persists across robust classifiers and substantially exceeds disagreement among human observers. Our findings show that adversarial robustness alone does not guarantee human-aligned categorization and suggest that robustness and human alignment should be evaluated as distinct properties of visual recognition systems. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC). Pagina del lavoro: https://arxiv.org/abs/2611.00715 — 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 2026-11-03T18:12:54.703Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).