Gender and Ethnicity Bias in Deep Learning

Gender and Ethnicity Bias in Deep Learning | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Gender and Ethnicity Bias in Deep Learning Ahsan Ul Islam, Israt Zarin, Tasnia Tabassum, Wadduwage Shanika Perera, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8321287/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract People's opinions and actions in everyday life are increasingly influenced by artificial intelligence. However, representation in the design of these technologies has the potential to quietly undo decades of progress in gender and ethnicity. These biases threaten the strides toward equality in these areas, casting a shadow over our progress. The concerns surrounding gender and ethnicity biases have pervaded numerous fields, none more prominently than within artificial intelligence, especially in pre-trained deep learning models. These models, celebrated for their ability to extract knowledge from extensive datasets, have immense potential to revolutionize society and decision-making. However, they are not impervious to the biases embedded in the data upon which they are trained. It raises the troubling possibility of unintentionally perpetuating and amplifying social biases linked to gender or ethnicity.The issue of gender bias in pre-trained deep learning models has gained significant traction in recent times. As these models have become increasingly ubiquitous across various applications, it has become evident that they often perpetuate and exacerbate long-standing gender biases inherent in the training data. This paper embarks on a methodical and empirically rigorous exploration, delving into the nuanced landscape of gender and ethnicity bias within a diverse array of pre-trained deep learning models. Through meticulous scrutiny of these models' performance about gender and ethnicity-based predictions, we aim to unearth invaluable insights regarding the presence, intricacies, and magnitude of bias.This research paper offers a comprehensive and empirically grounded examination of gender and ethnicity bias within a diverse range of pre-trained deep-learning models. This investigation involves a meticulous analysis of how these models perform when making predictions related to gender and ethnicity. By scrutinizing their predictions, the aim is to unearth valuable insights into the presence, nuances, and extent of these biases within AI systems.Furthermore, this work introduces an innovative, holistic solution to mitigate gender and ethnicity bias. We present CNN models strategically crafted to address and rectify biases about gender and ethnicity effectively. This model represents a pioneering step towards combating bias on multiple fronts within AI systems.This research thus contributes significantly to the broader understanding of bias within AI technologies. Simultaneously addressing gender and ethnicity bias and proposing a practical remedy and the way for more equitable and unbiased advancements in artificial intelligence. Through rigorous analysis and innovative solutions, we seek to ensure that AI systems respect and uphold the principles of fairness, inclusively, and diversity, thereby fostering a more just technological landscape for all. Gender Bias Ethnicity Bias Pre-Trained models Ma-chine Learning Neural Network Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8321287","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":561510720,"identity":"d45b5520-197b-4b0b-ab35-a21622646619","order_by":0,"name":"Ahsan Ul Islam","email":"","orcid":"","institution":"Sam Houston State University","correspondingAuthor":false,"prefix":"","firstName":"Ahsan","middleName":"Ul","lastName":"Islam","suffix":""},{"id":561510727,"identity":"17d08b4a-fdd7-4699-81dd-613a1839a8f2","order_by":1,"name":"Israt Zarin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAsUlEQVRIiWNgGAWjYBACNhCRwGAjx8DA3ADlEqclzZiBgZFILVBwOLGBaC18/IeffXi4gzl9w+3GBoYPZYeJcdgx4xmJZ9hyN9w52MA44xwxWhgbjBkS23hyN9xIbGDmbSNGCzP7Z6AWiXQDkJa/RGlh4wHZYpAA1sJIlBYenmKglgTDmUAtB3vOpRPWIt9/fDPjz7b/8nw3kg8++FFmTVgLCjhAovpRMApGwSgYBbgAAHEgOPzU2vqrAAAAAElFTkSuQmCC","orcid":"","institution":"University of Nebraska–Lincoln","correspondingAuthor":true,"prefix":"","firstName":"Israt","middleName":"","lastName":"Zarin","suffix":""},{"id":561510728,"identity":"1d84ab07-64e2-4090-a084-bcb3ce9cc70e","order_by":2,"name":"Tasnia Tabassum","email":"","orcid":"","institution":"Sam Houston State University","correspondingAuthor":false,"prefix":"","firstName":"Tasnia","middleName":"","lastName":"Tabassum","suffix":""},{"id":561510730,"identity":"fb76f1d6-44ec-4d06-bd5a-938af3b41ee1","order_by":3,"name":"Wadduwage Shanika Perera","email":"","orcid":"","institution":"Sam Houston State University","correspondingAuthor":false,"prefix":"","firstName":"Wadduwage","middleName":"Shanika","lastName":"Perera","suffix":""},{"id":561510735,"identity":"faa1609f-3e91-4ce8-9d0e-d147070a632f","order_by":4,"name":"Dr. ABM Islam","email":"","orcid":"","institution":"Sam Houston State University","correspondingAuthor":false,"prefix":"Dr.","firstName":"ABM","middleName":"","lastName":"Islam","suffix":""}],"badges":[],"createdAt":"2025-12-09 21:23:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8321287/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8321287/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98623898,"identity":"4dbb1f26-afc0-4ebb-ab5a-29f4a6f7146c","added_by":"auto","created_at":"2025-12-19 17:07:46","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8176,"visible":true,"origin":"","legend":"","description":"","filename":"5517847a6b424af489aec66a8bca4948.json","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/8d2f392160f08ad5f488408f.json"},{"id":98623359,"identity":"dee4773d-8f45-44de-8578-2c36c937d9d0","added_by":"auto","created_at":"2025-12-19 17:05:54","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":112125,"visible":true,"origin":"","legend":"","description":"","filename":"5517847a6b424af489aec66a8bca49481enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/b851ac42b62e30ffc698512c.xml"},{"id":98478682,"identity":"6186a9ff-f8c1-4c39-a848-36038da9d205","added_by":"auto","created_at":"2025-12-18 04:35:12","extension":"jpg","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":331108,"visible":true,"origin":"","legend":"","description":"","filename":"Fig3.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/cbc08b05e976c480024e5c9c.jpg"},{"id":98478679,"identity":"4f429487-df52-493d-b14c-17fdbd643eaf","added_by":"auto","created_at":"2025-12-18 04:35:12","extension":"jpg","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17507,"visible":true,"origin":"","legend":"","description":"","filename":"Fig4.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/3069e757cfd85a066c934501.jpg"},{"id":98478680,"identity":"1b159cad-86d9-49dc-a589-cd498acadb9b","added_by":"auto","created_at":"2025-12-18 04:35:12","extension":"jpg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15744,"visible":true,"origin":"","legend":"","description":"","filename":"Fig5.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/2b3440a9d593df3c9aaf341e.jpg"},{"id":98478684,"identity":"bc358558-236b-487d-a120-e264da6bf940","added_by":"auto","created_at":"2025-12-18 04:35:12","extension":"jpg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":171860,"visible":true,"origin":"","legend":"","description":"","filename":"Fig7.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/f88d6242c92535f8ec290f85.jpg"},{"id":98478687,"identity":"80ecb39d-cdfe-4c60-b54a-de373cd84496","added_by":"auto","created_at":"2025-12-18 04:35:12","extension":"jpg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":45166,"visible":true,"origin":"","legend":"","description":"","filename":"Fig1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/265d3aa44917bcfa86cc5992.jpg"},{"id":98478686,"identity":"889ff998-65da-45d5-b586-edc128044909","added_by":"auto","created_at":"2025-12-18 04:35:12","extension":"jpg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":112158,"visible":true,"origin":"","legend":"","description":"","filename":"Fig10.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/7bc72d1f0d52ab768cade8f3.jpg"},{"id":98478689,"identity":"18db2627-f63b-49b8-bf2a-a297e9ced9da","added_by":"auto","created_at":"2025-12-18 04:35:12","extension":"jpg","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":95926,"visible":true,"origin":"","legend":"","description":"","filename":"Fig9.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/4368d73510f80a27f417ab42.jpg"},{"id":98623579,"identity":"01bd8fb2-ac0d-413f-a55b-439a4f653d25","added_by":"auto","created_at":"2025-12-19 17:06:59","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33002,"visible":true,"origin":"","legend":"","description":"","filename":"SchematicdiagramofInceptionResNetV2modelcompressedview.png","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/e7db18386d8521f3c2df468a.png"},{"id":98623275,"identity":"28f3cec7-d61d-4954-afe8-0b0d62e7ae34","added_by":"auto","created_at":"2025-12-19 17:05:34","extension":"pdf","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2646853,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerNatureLaTeXTemplate4.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/178c2035fb0a3b48f24a556b.pdf"},{"id":98478693,"identity":"32e54ed4-7da6-4fed-a332-5014ecea5d8f","added_by":"auto","created_at":"2025-12-18 04:35:12","extension":"jpg","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":79533,"visible":true,"origin":"","legend":"","description":"","filename":"VGG16.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/d07178eeeca4becbf66e44d3.jpg"},{"id":98624400,"identity":"77dd338b-a30c-460a-ab1c-c83e7c83b61d","added_by":"auto","created_at":"2025-12-19 17:08:23","extension":"jpg","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":103328,"visible":true,"origin":"","legend":"","description":"","filename":"VGG19.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/ed61c1c259dbafe5b8aedb23.jpg"},{"id":98624538,"identity":"be13d5de-0742-4852-93c8-a8beea31baf2","added_by":"auto","created_at":"2025-12-19 17:08:30","extension":"eps","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2890,"visible":true,"origin":"","legend":"","description":"","filename":"empty.eps","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/6166bf31f19c57015ac0b9de.eps"},{"id":98623794,"identity":"c3c9e568-34aa-4447-b99e-0cc034c2cb4a","added_by":"auto","created_at":"2025-12-19 17:07:34","extension":"eps","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":91593,"visible":true,"origin":"","legend":"","description":"","filename":"fig.eps","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/bba00f02d04fb612d0a7f26b.eps"},{"id":98478702,"identity":"200beb4f-f90b-4429-bab9-e62779ac9bb1","added_by":"auto","created_at":"2025-12-18 04:35:12","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":951059,"visible":true,"origin":"","legend":"","description":"","filename":"fig2.png","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/b274729e2f5c7f8842d3efcc.png"},{"id":98478690,"identity":"5553c63a-d619-4d07-8bba-92f327be4a77","added_by":"auto","created_at":"2025-12-18 04:35:12","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":66950,"visible":true,"origin":"","legend":"","description":"","filename":"fig6.png","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/c9fb0d99c861d8b1d716adb3.png"},{"id":98624186,"identity":"aa0c0789-25d2-4fe6-b216-87c0480965b6","added_by":"auto","created_at":"2025-12-19 17:08:07","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16291,"visible":true,"origin":"","legend":"","description":"","filename":"fig7.png","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/405c64195fadc4cc3af76ff4.png"},{"id":98478703,"identity":"3e9aa99e-4ef8-4720-87e0-6c50863bf0ca","added_by":"auto","created_at":"2025-12-18 04:35:12","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15451,"visible":true,"origin":"","legend":"","description":"","filename":"fig8.png","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/79aa05d2288603723ae4dc1f.png"},{"id":98623504,"identity":"583c709b-da70-4fe1-91d3-455c5dea7e7f","added_by":"auto","created_at":"2025-12-19 17:06:35","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":28587,"visible":true,"origin":"","legend":"","description":"","filename":"fig9.png","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/d3b72ce6ad604f04cbb55261.png"},{"id":98478697,"identity":"62c96384-9996-40de-b5fc-5eb269c405f1","added_by":"auto","created_at":"2025-12-18 04:35:12","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":102611,"visible":true,"origin":"","legend":"","description":"","filename":"inceptionv3oncoview.png","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/69cad1fb99ecf4a44485a904.png"},{"id":98478707,"identity":"a0ba1300-7c54-43f9-8d68-0aa482775f2d","added_by":"auto","created_at":"2025-12-18 04:35:13","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":252743,"visible":true,"origin":"","legend":"","description":"","filename":"resnetarchitecture.png","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/2338e0d2c9479e0686fe3c0f.png"},{"id":98478692,"identity":"4ecc63f7-e550-4621-9be7-6816c1ed0e53","added_by":"auto","created_at":"2025-12-18 04:35:12","extension":"bst","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":146013,"visible":true,"origin":"","legend":"","description":"","filename":"snapacite.bst","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/436c9414d9ecc82e77e0c9d1.bst"},{"id":98478701,"identity":"861c7b59-397f-46e6-ac18-d9d6fd934865","added_by":"auto","created_at":"2025-12-18 04:35:12","extension":"bst","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29828,"visible":true,"origin":"","legend":"","description":"","filename":"snaps.bst","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/28dab15f1d236c41f60386ba.bst"},{"id":98478709,"identity":"0993b4ec-6e02-4645-832f-2f17515a5d14","added_by":"auto","created_at":"2025-12-18 04:35:13","extension":"pdf","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":421391,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/43dfcaf3d3e1cefc1957f809.pdf"},{"id":98624019,"identity":"66702faf-9e94-4041-aa4a-eb36a9ca357a","added_by":"auto","created_at":"2025-12-19 17:07:54","extension":"bst","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35515,"visible":true,"origin":"","legend":"","description":"","filename":"snbasic.bst","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/62a459ed62af61d2414fcc81.bst"},{"id":98624029,"identity":"44dee0d5-35b8-43ad-b519-c6fd52d9759e","added_by":"auto","created_at":"2025-12-19 17:07:55","extension":"bst","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33968,"visible":true,"origin":"","legend":"","description":"","filename":"snchicago.bst","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/27383a4a088d320dfce2106f.bst"},{"id":98478708,"identity":"10bdd7c3-ef0f-4e4b-9261-28e24401cdfe","added_by":"auto","created_at":"2025-12-18 04:35:13","extension":"cls","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55857,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/799145cff47d9ca2a88ff400.cls"},{"id":98478704,"identity":"9e61f643-3d33-4441-950e-a182c4d1bc99","added_by":"auto","created_at":"2025-12-18 04:35:12","extension":"bst","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64023,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysay.bst","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/5778e796a24636ce3bf40425.bst"},{"id":98478705,"identity":"ed8bf090-1f02-4b53-a693-1ad813b8509f","added_by":"auto","created_at":"2025-12-18 04:35:12","extension":"bst","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64166,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/9b9727a4d447616dbafa8bd8.bst"},{"id":98478699,"identity":"a5833fb6-dcb6-479a-acca-0029376d63df","added_by":"auto","created_at":"2025-12-18 04:35:12","extension":"bst","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37333,"visible":true,"origin":"","legend":"","description":"","filename":"snnature.bst","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/231f2f1b42168f64b0c58271.bst"},{"id":98624525,"identity":"3c7abd5c-74f6-41fd-a064-b500bfae988d","added_by":"auto","created_at":"2025-12-19 17:08:29","extension":"bst","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39951,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouveray.bst","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/e2459e5c0ff9c14d24520f40.bst"},{"id":98478710,"identity":"cd37f902-6866-4769-9fb0-5cb3d664a175","added_by":"auto","created_at":"2025-12-18 04:35:13","extension":"bst","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40758,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouvernum.bst","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/ad028974c54378b50a165d82.bst"},{"id":98478715,"identity":"93a2c1b7-a15e-434e-a0ac-4a57485a0bd2","added_by":"auto","created_at":"2025-12-18 04:35:13","extension":"pdf","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":418495,"visible":true,"origin":"","legend":"","description":"","filename":"usermanual.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/661a9c10043400b1ed438317.pdf"},{"id":98478706,"identity":"5dedb0ac-a359-47ca-bbd8-217e67625939","added_by":"auto","created_at":"2025-12-18 04:35:13","extension":"xml","order_by":50,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":124225,"visible":true,"origin":"","legend":"","description":"","filename":"5517847a6b424af489aec66a8bca49481structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/be9d867e17328be6d34e2fa3.xml"},{"id":98478713,"identity":"920e773f-9084-42a4-86c2-12df93fd5e75","added_by":"auto","created_at":"2025-12-18 04:35:13","extension":"html","order_by":51,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":131505,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1/40bb78e1af78cfce08c5dd1d.html"},{"id":104393602,"identity":"c0841306-e517-4455-a987-32a549224629","added_by":"auto","created_at":"2026-03-11 10:42:16","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1832599,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerNatureLaTeXTemplate4.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8321287/v1_covered_610d036a-85d0-4b8a-b880-ce1d641abab8.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Gender and Ethnicity Bias in Deep Learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Gender Bias, Ethnicity Bias, Pre-Trained models, Ma-chine Learning, Neural Network","lastPublishedDoi":"10.21203/rs.3.rs-8321287/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8321287/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003ePeople's opinions and actions in everyday life are increasingly influenced by artificial intelligence. However, representation in the design of these technologies has the potential to quietly undo decades of progress in gender and ethnicity. These biases threaten the strides toward equality in these areas, casting a shadow over our progress. The concerns surrounding gender and ethnicity biases have pervaded numerous fields, none more prominently than within artificial intelligence, especially in pre-trained deep learning models. These models, celebrated for their ability to extract knowledge from extensive datasets, have immense potential to revolutionize society and decision-making. However, they are not impervious to the biases embedded in the data upon which they are trained. It raises the troubling possibility of unintentionally perpetuating and amplifying social biases linked to gender or ethnicity.The issue of gender bias in pre-trained deep learning models has gained significant traction in recent times. As these models have become increasingly ubiquitous across various applications, it has become evident that they often perpetuate and exacerbate long-standing gender biases inherent in the training data. This paper embarks on a methodical and empirically rigorous exploration, delving into the nuanced landscape of gender and ethnicity bias within a diverse array of pre-trained deep learning models. Through meticulous scrutiny of these models' performance about gender and ethnicity-based predictions, we aim to unearth invaluable insights regarding the presence, intricacies, and magnitude of bias.This research paper offers a comprehensive and empirically grounded examination of gender and ethnicity bias within a diverse range of pre-trained deep-learning models. This investigation involves a meticulous analysis of how these models perform when making predictions related to gender and ethnicity. By scrutinizing their predictions, the aim is to unearth valuable insights into the presence, nuances, and extent of these biases within AI systems.Furthermore, this work introduces an innovative, holistic solution to mitigate gender and ethnicity bias. We present CNN models strategically crafted to address and rectify biases about gender and ethnicity effectively. This model represents a pioneering step towards combating bias on multiple fronts within AI systems.This research thus contributes significantly to the broader understanding of bias within AI technologies. Simultaneously addressing gender and ethnicity bias and proposing a practical remedy and the way for more equitable and unbiased advancements in artificial intelligence. Through rigorous analysis and innovative solutions, we seek to ensure that AI systems respect and uphold the principles of fairness, inclusively, and diversity, thereby fostering a more just technological landscape for all.\u003c/p\u003e","manuscriptTitle":"Gender and Ethnicity Bias in Deep Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-18 04:35:07","doi":"10.21203/rs.3.rs-8321287/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"12417d7a-2102-4552-b728-11eada081941","owner":[],"postedDate":"December 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-11T10:39:30+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-18 04:35:07","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8321287","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8321287","identity":"rs-8321287","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}