{"id":19375,"date":"2026-09-29T15:01:26","date_gmt":"2026-09-29T19:01:26","guid":{"rendered":"https:\/\/www.iri.com\/blog\/?p=19375"},"modified":"2026-09-29T15:01:26","modified_gmt":"2026-09-29T19:01:26","slug":"automated-facial-redaction-biometric-data","status":"publish","type":"post","link":"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/","title":{"rendered":"How to Automate Facial Redaction to Protect Biometric Data"},"content":{"rendered":"<h2>Quick Summary<\/h2>\n<p><a href=\"https:\/\/www.iri.com\/news\/press-releases\/iri-announces-version-7-of-the-darkshield-data-masking-tool\">DarkShield Version 7<\/a> introduces an automated facial detection and redaction feature built on the high-performance SCRFD model from InsightFace. This integration enables organizations to identify and obfuscate faces in standalone images and embedded documents, helping teams meet privacy compliance requirements for biometric PII under regulations such as GDPR and HIPAA with minimal manual configuration.<\/p>\n<h2>The Challenge of Protecting Biometric Data<\/h2>\n<p>As privacy regulations such as GDPR and HIPAA address sensitive personal information, biometric data, including facial imagery, requires careful protection. HIPAA specifically identifies full-face photographs and comparable images as identifiers associated with Protected Health Information (PHI).<\/p>\n<p>Protecting facial data at enterprise scale can be difficult when organizations rely on manual redaction. Manually identifying and obscuring faces across large collections of documents is slow, error-prone, and difficult to sustain within broader data governance processes.<\/p>\n<p>DarkShield V7 addresses this challenge with an automated facial detection matcher that integrates directly into existing data protection workflows<\/p>\n<p>Behind the scenes, DarkShield uses the <strong>Single-Shot Scale-Aware Face Detector (SCRFD)<\/strong> AI model from InsightFace. IRI selected SCRFD for its balance of speed, size, and detection accuracy. The integration enables the DarkShield engine to automatically detect multiple faces across varied file formats and immediately apply black-box redaction.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-19378 aligncenter\" src=\"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/before-after-black-box-redaction-1024x576.png\" alt=\"Group photo before and after DarkShield automatically redacts detected faces\" width=\"795\" height=\"447\" srcset=\"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/before-after-black-box-redaction-1024x576.png 1024w, https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/before-after-black-box-redaction-300x169.png 300w, https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/before-after-black-box-redaction-768x432.png 768w, https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/before-after-black-box-redaction-1536x864.png 1536w, https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/before-after-black-box-redaction.png 1110w\" sizes=\"(max-width: 795px) 100vw, 795px\" \/><\/p>\n<h2>How to Use DarkShield to Find and Mask Faces<\/h2>\n<p>Because <a href=\"https:\/\/www.iri.com\/products\/darkshield\">DarkShield<\/a> is a self-hosted solution, your sensitive visual data never leaves your secure environment, ensuring data sovereignty remains intact while meeting compliance goals.<\/p>\n<p>Because job design efficiency is central to DarkShield, configuration is simple.<\/p>\n<ol>\n<li>Open the <strong><a href=\"https:\/\/www.iri.com\/products\/workbench\/darkshield-gui\/classify\">Data Class and Rule Library<\/a> <\/strong>in IRI Workbench<\/li>\n<li>Navigate to the <strong>Data Matcher<\/strong> page.<\/li>\n<li>Select <strong>Detect Faces<\/strong> from the matcher type dropdown menu.<\/li>\n<\/ol>\n<p>No complex fine-tuning parameters are required.\u00a0Selecting this option allows the engine to apply the matcher to your job immediately. This simplicity allows teams to scale facial redaction across millions of files without creating operational overhead.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-19380 aligncenter\" src=\"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/image1.png\" alt=\"IRI Workbench Data Class Details showing a Face data class with the facedetect data matcher configured\" width=\"608\" height=\"410\" srcset=\"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/image1.png 836w, https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/image1-300x202.png 300w, https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/image1-768x518.png 768w\" sizes=\"(max-width: 608px) 100vw, 608px\" \/><\/p>\n<p style=\"text-align: center;\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-19382\" src=\"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/detectfaces.png\" alt=\"IRI Workbench Data Matcher dialog with Detect Faces selected as the matcher type\" width=\"444\" height=\"389\" srcset=\"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/detectfaces.png 502w, https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/detectfaces-300x263.png 300w\" sizes=\"(max-width: 444px) 100vw, 444px\" \/><\/p>\n<h2>Automating Facial Detection Through API and CLI Jobs<\/h2>\n<p>For enterprise workflows requiring programmatic control, DarkShield allows you to <a href=\"https:\/\/www.iri.com\/products\/workbench\/darkshield-gui\/cli-api\">export job specifications<\/a> for API or CLI jobs directly from the GUI or define them as code. The search and masking job specs for API calls follow a straightforward <a href=\"https:\/\/www.iri.com\/blog\/data-protection\/iri-darkshield-rest-api\/\">JSON structure<\/a>.<\/p>\n<p>The face matcher resides within the <code dir=\"ltr\">FileSearchContext<\/code>location:<\/p>\n<p style=\"text-align: center;\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-19384\" src=\"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/image4.png\" alt=\"JSON FileSearchContext configuration showing the DarkShield detect_face matcher for facial detection\" width=\"325\" height=\"306\" \/><\/p>\n<p>This configuration identifies the facial data class and uses the <code dir=\"ltr\">detect_face<\/code> matcher within the file search context.<\/p>\n<p>The same job design can be incorporated into existing schedulers and CI\/CD pipelines. This allows facial detection and obfuscation to become an automated step within a broader DarkShield data masking implementation rather than a separate manual process.<\/p>\n<h2>Facial Redaction for Embedded Images and Documents<\/h2>\n<p>DarkShield\u2019s discovery engine can handle embedded images within a wide range of file types, including PDFs, Microsoft Office documents, and compressed archives. It extracts the visual content, applies facial redaction, and preserves the file&#8217;s original structure.<\/p>\n<p>Because DarkShield is self-hosted and on-premises, sensitive imagery remains within the organization\u2019s secure infrastructure during the detection and redaction process. This removes the need to upload that data to third-party APIs.<\/p>\n<p style=\"text-align: center;\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone  wp-image-19387\" src=\"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/Facial-Redaction-for-Embedded-Images-and-Documents-1024x490.png\" alt=\"Workflow diagram showing PDF, Word, and ZIP files leading to an embedded image, followed by the same image with the face redacted and a privacy shield icon\" width=\"435\" height=\"208\" srcset=\"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/Facial-Redaction-for-Embedded-Images-and-Documents-1024x490.png 1024w, https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/Facial-Redaction-for-Embedded-Images-and-Documents-300x144.png 300w, https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/Facial-Redaction-for-Embedded-Images-and-Documents-768x368.png 768w, https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/Facial-Redaction-for-Embedded-Images-and-Documents-1536x735.png 1536w, https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/Facial-Redaction-for-Embedded-Images-and-Documents.png 1110w, https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/Facial-Redaction-for-Embedded-Images-and-Documents-730x350.png 730w\" sizes=\"(max-width: 435px) 100vw, 435px\" \/><\/p>\n<h2><span style=\"font-weight: 400;\">Frequently Asked Questions (FAQ)<\/span><\/h2>\n<h3><b>Why does Facial Redaction Matter?<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">As privacy regulations (GDPR\/HIPAA) evolve to include biometric data, manual redaction is no longer viable. DarkShield provides a self-hosted, scalable solution that protects PII\/PHI without requiring your data to leave your secure environment.<\/span><\/p>\n<h3><b>How does DarkShield distinguish between a human face and other image elements?<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">DarkShield utilizes the advanced SCRFD model, which is specifically trained to isolate human facial features within complex images. This specialized training significantly minimizes false positives compared to generic object detection models, ensuring higher accuracy in your redaction outputs.<\/span><\/p>\n<h3>Does facial detection require extensive model configuration?<\/h3>\n<p>No. In IRI Workbench, users configure the feature by adding a Data Matcher and selecting Detect Faces as the matcher type. The original workflow does not require additional complex fine-tuning parameters.<\/p>\n<h3><b>Can DarkShield redact faces inside compressed or embedded file formats?<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">Yes. DarkShield can process embedded images within supported file types, including PDFs, Microsoft Office documents, and compressed archives. It extracts the visual content, performs facial redaction, and handles the file within its original structure. <\/span><\/p>\n<h3><b>Do I need to host my data on a public cloud to use this feature?<\/b><\/h3>\n<p>No. DarkShield is self-hosted and can operate on-premises.\u00a0<span style=\"font-weight: 400;\">Your data stays within your secure infrastructure during the entire detection and redaction process. This is a key advantage for teams managing strict compliance rules, such as HIPAA or data sovereignty requirements, as it eliminates the need to upload sensitive imagery to third-party APIs.<\/span><\/p>\n<p>If you have questions or need assistance with facial detection and obfuscation in a DarkShield discovery and deidentification project, contact <a href=\"mailto:darkshield@iri.com\">darkshield@iri.com<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Quick Summary DarkShield Version 7 introduces an automated facial detection and redaction feature built on the high-performance SCRFD model from InsightFace. This integration enables organizations to identify and obfuscate faces in standalone images and embedded documents, helping teams meet privacy compliance requirements for biometric PII under regulations such as GDPR and HIPAA with minimal manual<\/p>\n<div><a class=\"btn-filled btn\" href=\"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/\" title=\"How to Automate Facial Redaction to Protect Biometric Data\">Read More<\/a><\/div>\n","protected":false},"author":152,"featured_media":19388,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_exactmetrics_skip_tracking":false,"_exactmetrics_sitenote_active":false,"_exactmetrics_sitenote_note":"","_exactmetrics_sitenote_category":0,"footnotes":""},"categories":[8],"tags":[2493,2494,1386,14,18,2068,2492,2491,1743,2128,2496,2129,1815,2495],"class_list":["post-19375","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-data-protection","tag-biometric-data","tag-biometric-pii","tag-darkshield","tag-data-masking","tag-data-privacy","tag-data-redaction","tag-facial-detection","tag-facial-redaction","tag-gdpr-compliance","tag-hipaa-compliance","tag-insightface","tag-phi-protection","tag-pii-protection","tag-scrfd"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v23.4 (Yoast SEO v23.4) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Automated Facial Redaction for Biometric Data | IRI DarkShield<\/title>\n<meta name=\"description\" content=\"Learn how IRI DarkShield V7 uses automated facial detection and redaction to protect biometric PII and PHI in images, documents, and archives.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"How to Automate Facial Redaction to Protect Biometric Data\" \/>\n<meta property=\"og:description\" content=\"Learn how IRI DarkShield V7 uses automated facial detection and redaction to protect biometric PII and PHI in images, documents, and archives.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/\" \/>\n<meta property=\"og:site_name\" content=\"IRI\" \/>\n<meta property=\"article:published_time\" content=\"2026-09-29T19:01:26+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/featured-image-facial-detection.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1056\" \/>\n\t<meta property=\"og:image:height\" content=\"506\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Adam Lewis\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Adam Lewis\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/\"},\"author\":{\"name\":\"Adam Lewis\",\"@id\":\"https:\/\/www.iri.com\/blog\/#\/schema\/person\/37c0e5beab094bd61cc521902df2876e\"},\"headline\":\"How to Automate Facial Redaction to Protect Biometric Data\",\"datePublished\":\"2026-09-29T19:01:26+00:00\",\"dateModified\":\"2026-09-29T19:01:26+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/\"},\"wordCount\":767,\"publisher\":{\"@id\":\"https:\/\/www.iri.com\/blog\/#organization\"},\"image\":{\"@id\":\"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/featured-image-facial-detection.png\",\"keywords\":[\"biometric data\",\"biometric PII\",\"DarkShield\",\"data masking\",\"data privacy\",\"data redaction\",\"facial detection\",\"facial redaction\",\"gdpr compliance\",\"HIPAA Compliance\",\"InsightFace\",\"PHI Protection\",\"PII protection\",\"SCRFD\"],\"articleSection\":[\"Data Masking\/Protection\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/\",\"url\":\"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/\",\"name\":\"Automated Facial Redaction for Biometric Data | IRI DarkShield\",\"isPartOf\":{\"@id\":\"https:\/\/www.iri.com\/blog\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/featured-image-facial-detection.png\",\"datePublished\":\"2026-09-29T19:01:26+00:00\",\"dateModified\":\"2026-09-29T19:01:26+00:00\",\"description\":\"Learn how IRI DarkShield V7 uses automated facial detection and redaction to protect biometric PII and PHI in images, documents, and archives.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/#primaryimage\",\"url\":\"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/featured-image-facial-detection.png\",\"contentUrl\":\"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/featured-image-facial-detection.png\",\"width\":1056,\"height\":506,\"caption\":\"Illustration of a redacted face inside a detection frame with a shield lock icon and faded PDF, Word, and ZIP files in the background\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.iri.com\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"How to Automate Facial Redaction to Protect Biometric Data\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.iri.com\/blog\/#website\",\"url\":\"https:\/\/www.iri.com\/blog\/\",\"name\":\"IRI\",\"description\":\"Total Data Management Blog\",\"publisher\":{\"@id\":\"https:\/\/www.iri.com\/blog\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.iri.com\/blog\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.iri.com\/blog\/#organization\",\"name\":\"IRI\",\"url\":\"https:\/\/www.iri.com\/blog\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.iri.com\/blog\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2019\/02\/iri-logo-total-data-management-small-1.png\",\"contentUrl\":\"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2019\/02\/iri-logo-total-data-management-small-1.png\",\"width\":750,\"height\":206,\"caption\":\"IRI\"},\"image\":{\"@id\":\"https:\/\/www.iri.com\/blog\/#\/schema\/logo\/image\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.iri.com\/blog\/#\/schema\/person\/37c0e5beab094bd61cc521902df2876e\",\"name\":\"Adam Lewis\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.iri.com\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/087667d0c75d33bb6fab6e734bd89333?s=96&d=blank&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/087667d0c75d33bb6fab6e734bd89333?s=96&d=blank&r=g\",\"caption\":\"Adam Lewis\"},\"url\":\"https:\/\/www.iri.com\/blog\/author\/adaml\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Automated Facial Redaction for Biometric Data | IRI DarkShield","description":"Learn how IRI DarkShield V7 uses automated facial detection and redaction to protect biometric PII and PHI in images, documents, and archives.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/","og_locale":"en_US","og_type":"article","og_title":"How to Automate Facial Redaction to Protect Biometric Data","og_description":"Learn how IRI DarkShield V7 uses automated facial detection and redaction to protect biometric PII and PHI in images, documents, and archives.","og_url":"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/","og_site_name":"IRI","article_published_time":"2026-09-29T19:01:26+00:00","og_image":[{"width":1056,"height":506,"url":"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/featured-image-facial-detection.png","type":"image\/png"}],"author":"Adam Lewis","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Adam Lewis","Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/#article","isPartOf":{"@id":"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/"},"author":{"name":"Adam Lewis","@id":"https:\/\/www.iri.com\/blog\/#\/schema\/person\/37c0e5beab094bd61cc521902df2876e"},"headline":"How to Automate Facial Redaction to Protect Biometric Data","datePublished":"2026-09-29T19:01:26+00:00","dateModified":"2026-09-29T19:01:26+00:00","mainEntityOfPage":{"@id":"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/"},"wordCount":767,"publisher":{"@id":"https:\/\/www.iri.com\/blog\/#organization"},"image":{"@id":"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/#primaryimage"},"thumbnailUrl":"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/featured-image-facial-detection.png","keywords":["biometric data","biometric PII","DarkShield","data masking","data privacy","data redaction","facial detection","facial redaction","gdpr compliance","HIPAA Compliance","InsightFace","PHI Protection","PII protection","SCRFD"],"articleSection":["Data Masking\/Protection"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/","url":"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/","name":"Automated Facial Redaction for Biometric Data | IRI DarkShield","isPartOf":{"@id":"https:\/\/www.iri.com\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/#primaryimage"},"image":{"@id":"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/#primaryimage"},"thumbnailUrl":"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/featured-image-facial-detection.png","datePublished":"2026-09-29T19:01:26+00:00","dateModified":"2026-09-29T19:01:26+00:00","description":"Learn how IRI DarkShield V7 uses automated facial detection and redaction to protect biometric PII and PHI in images, documents, and archives.","breadcrumb":{"@id":"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/#primaryimage","url":"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/featured-image-facial-detection.png","contentUrl":"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/featured-image-facial-detection.png","width":1056,"height":506,"caption":"Illustration of a redacted face inside a detection frame with a shield lock icon and faded PDF, Word, and ZIP files in the background"},{"@type":"BreadcrumbList","@id":"https:\/\/www.iri.com\/blog\/data-protection\/automated-facial-redaction-biometric-data\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.iri.com\/blog\/"},{"@type":"ListItem","position":2,"name":"How to Automate Facial Redaction to Protect Biometric Data"}]},{"@type":"WebSite","@id":"https:\/\/www.iri.com\/blog\/#website","url":"https:\/\/www.iri.com\/blog\/","name":"IRI","description":"Total Data Management Blog","publisher":{"@id":"https:\/\/www.iri.com\/blog\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.iri.com\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.iri.com\/blog\/#organization","name":"IRI","url":"https:\/\/www.iri.com\/blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.iri.com\/blog\/#\/schema\/logo\/image\/","url":"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2019\/02\/iri-logo-total-data-management-small-1.png","contentUrl":"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2019\/02\/iri-logo-total-data-management-small-1.png","width":750,"height":206,"caption":"IRI"},"image":{"@id":"https:\/\/www.iri.com\/blog\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/www.iri.com\/blog\/#\/schema\/person\/37c0e5beab094bd61cc521902df2876e","name":"Adam Lewis","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.iri.com\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/087667d0c75d33bb6fab6e734bd89333?s=96&d=blank&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/087667d0c75d33bb6fab6e734bd89333?s=96&d=blank&r=g","caption":"Adam Lewis"},"url":"https:\/\/www.iri.com\/blog\/author\/adaml\/"}]}},"jetpack_featured_media_url":"https:\/\/www.iri.com\/blog\/wp-content\/uploads\/2026\/09\/featured-image-facial-detection.png","_links":{"self":[{"href":"https:\/\/www.iri.com\/blog\/wp-json\/wp\/v2\/posts\/19375"}],"collection":[{"href":"https:\/\/www.iri.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.iri.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.iri.com\/blog\/wp-json\/wp\/v2\/users\/152"}],"replies":[{"embeddable":true,"href":"https:\/\/www.iri.com\/blog\/wp-json\/wp\/v2\/comments?post=19375"}],"version-history":[{"count":7,"href":"https:\/\/www.iri.com\/blog\/wp-json\/wp\/v2\/posts\/19375\/revisions"}],"predecessor-version":[{"id":19389,"href":"https:\/\/www.iri.com\/blog\/wp-json\/wp\/v2\/posts\/19375\/revisions\/19389"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.iri.com\/blog\/wp-json\/wp\/v2\/media\/19388"}],"wp:attachment":[{"href":"https:\/\/www.iri.com\/blog\/wp-json\/wp\/v2\/media?parent=19375"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.iri.com\/blog\/wp-json\/wp\/v2\/categories?post=19375"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.iri.com\/blog\/wp-json\/wp\/v2\/tags?post=19375"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}