{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:35:53Z","timestamp":1761176153670,"version":"build-2065373602"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686318","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,21]]},"abstract":"<jats:p>Saliency-map explanations are intended to make computer-vision models more transparent, but it is unclear whether they help people recognise biased behaviour. We conducted a controlled on-line study with 40 participants who compared Layer-wise Relevance Propagation maps from convolutional face-recognition models. A fair model was trained on a balanced synthetic dataset; two biased models were trained on data in which either light- or dark-skinned faces appeared only in frontal pose. Each participant completed 32 comparison trials. When the fair model was paired with the dark-skinned-pose-biased model, selections were near chance (52.8% favouring the fair model, binomial p = .36). When the fair model was paired with the light-skinned-pose-biased model, participants chose the biased model significantly more often (58.1%, p = .005). Confidence ratings varied with condition and did not systematically track model fairness. These results indicate that pixel-level attribution alone does not reliably expose training bias and can, in some settings, mislead non-expert users.<\/jats:p>","DOI":"10.3233\/faia250936","type":"book-chapter","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:46:28Z","timestamp":1761126388000},"source":"Crossref","is-referenced-by-count":0,"title":["Do Explanations Expose Bias? How Saliency Maps Affect Judgements of Biased Face-Recognition Models"],"prefix":"10.3233","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8980-0685","authenticated-orcid":false,"given":"Justyn","family":"Rodrigues","sequence":"first","affiliation":[{"name":"Western Sydney University, Penrith NSW 2751, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2247-3020","authenticated-orcid":false,"given":"Krista A.","family":"Ehinger","sequence":"additional","affiliation":[{"name":"The University of Melbourne, Parkville VIC 3010, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8284-2062","authenticated-orcid":false,"given":"Oliver","family":"Obst","sequence":"additional","affiliation":[{"name":"Western Sydney University, Penrith NSW 2751, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5454-6197","authenticated-orcid":false,"given":"X. Rosalind","family":"Wang","sequence":"additional","affiliation":[{"name":"Western Sydney University, Penrith NSW 2751, Australia"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA250936","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:46:29Z","timestamp":1761126389000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA250936"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9781643686318"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia250936","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}