{"id":15349,"date":"2025-03-25T10:36:56","date_gmt":"2025-03-25T09:36:56","guid":{"rendered":"https:\/\/www.uni.lu\/snt-en\/?post_type=news&p=15349"},"modified":"2025-12-11T17:14:28","modified_gmt":"2025-12-11T16:14:28","slug":"a-race-against-deepfakes","status":"publish","type":"news","link":"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/","title":{"rendered":"A race against deepfakes: how AI is fighting AI"},"content":{"rendered":"\n
\n

Every five minutes, somewhere in the world, someone creates a new deepfake. As this AI-powered threat grows, researchers are developing equally powerful tools to fight back.<\/strong><\/p>\n\n\n\n

In 2024, a deepfake attempt occurred every five minutes, according to a report by the Entrust Cybersecurity Institute. The report shows a worrying trend. Fraudsters mix new and old techniques to beat new defense strategies. Criminals use stolen personally identifiable information (PII) from data breaches or phishing. Then, they create hyper-realistic synthetic identities.<\/p>\n\n\n\n

Deepfakes use artificial intelligence to create convincing but fake videos, images, or audio. They can make people appear to say or do things they never did, from celebrity impersonations to fake news videos featuring political figures. The technology has advanced so quickly that spotting fakes has become increasingly difficult for the human eye.<\/p>\n\n\n\n

The good news is that researchers are using powerful AI models to respond to these AI threats. Researchers at the University of Luxembourg\u2019s Interdisciplinary Centre for Security, Reliability and Trust (SnT) have been developing advanced AI models to detect deepfakes since 2022.<\/p>\n\n\n\n

Their goal is clear: make deepfake detection faster, more accurate, and more resilient against evolving threats.<\/p>\n\n\n\n

\nThe role of SnT in deepfake detection<\/h2>\n\n\n\n

In 2021, scientists partnered up with Post Luxembourg to develop an algorithm to detect face-swap deepfakes that was more robust and effective than the solutions available on the market at the time. Building on this success, the research was expanded under the Luxembourg National Research Fund (FNR) BRIDGES programme, followed by an industrial fellowship with Post Luxembourg, concluding in March 2025. These initiatives have helped refine deepfake detection methods, allowing researchers to tackle increasingly sophisticated AI-generated content.<\/p>\n\n\n\n

\nHow AI detects deepfakes<\/h2>\n\n\n\n

To identify deepfakes, deepfake AI tools (or AI models) must be trained to detect inconsistencies in photos and videos – subtle details that bear the mark of AI-generated artifacts. For instance, generative AI models often struggle with fine details like hands and fingers<\/a>, making these areas prime indicators of forgery.<\/p>\n\n\n\n

AI models are usually trained through a method known as binary classification, where data is categorised into two groups: real or fake. For instance, researchers present the model with a series of images, each labelled as either real or fake. Through repeated exposure, it gradually learns to recognise patterns that distinguish authentic images from manipulated ones. However, this approach has a drawback: during training, the model tends to also learn patterns in the data that are not important.<\/p>\n\n\n\n

\u201cFor example, if a model is trained on images that mostly have a white background, it might fail when trying to analyse photos with black backgrounds,\u201d explains Dr. Enjie Ghorbel, a researcher in the Computer Vision, Imaging, and Machine Intelligence Research Group (CVI2). This issue, known in deep learning as a generalisation problem, limits the model\u2019s ability to adapt to new contexts.<\/p>\n\n\n\n

\u201cOur research found that, instead of training models to separate fake from real, we could focus on teaching them to look for real data only,\u201d says Ghorbel. \u201cIf the data examined doesn\u2019t align with the patterns of real data, it means that it\u2019s fake. This approach makes the model more robust and agnostic to various types of deepfakes. We explored this research direction first with images, then with videos,\u201d she adds.<\/p>\n\n\n\n

In their research, the CVI2 researchers \u2013 Prof. Djamila Aouada<\/a> (PI), Dr. Enjie Ghorbel, Dr. Anis Kacem<\/a>, PhD students Van Dat Nguyen<\/a> and Nesryne Mejri<\/a>, as well as postdoc researchers Dr. Marcella Astrid<\/a> and Dr. Niki Foteinopoulou – had to develop ever more effective logical arguments to counter the increasingly sophisticated methods used to create deepfakes. These included training the AI to focus on vulnerable areas in images and checking the synchronisation between audio and video tracks.<\/p>\n\n\n\n

\u201cBy adding other learning objectives, we have achieved a higher level of generalisation in our models,\u201d explains Ghorbel.<\/p>\n\n\n\n

\nThe challenge of fully synthetic data<\/h2>\n\n\n\n

As deepfake AI advances, a new challenge has emerged: fully AI-generated images and videos. Unlike traditional deepfakes that modify existing media, these are entirely synthetic. This shift makes detection even more difficult. The photo below shows two individuals. But only one really exists, the other is AI-generated. Can you guess which one is real?<\/p>\n\n\n

\n \n\"Deepfake <\/figure>\n\n\n

\u201cMost deepfake detectors today work well on face-swapping and face reenactment,\u201d says Ghorbel, \u201cbut they don’t work at all on fully synthetic data. This is the level of generalisation that we would like to reach,\u201d she explains.<\/p>\n\n\n\n

To tackle this issue, the CVI2 team turned to multitask learning – a method that trains AI to evaluate multiple aspects of an image or video simultaneously. Instead of just classifying content as simply real or fake, the model examines multiple aspects of the image, such as identifying the location of forgeries,\u201d providing additional context to evaluate their authenticity.<\/p>\n\n\n\n

\nThe real-world impact of deepfake detection<\/h2>\n\n\n\n

Deepfake detection has numerous applications, with bank fraud and fake news representing some of the greatest risks to society. Fake images are also used for blackmail, coercion, and insurance fraud. As digitalisation grows, these criminal activities could slow down many sectors. The impact could be significant.<\/p>\n\n\n\n

As AI grows stronger, fraudsters get better tools. This makes strong detection methods, and these research projects, crucial to protect businesses and people.<\/p>\n\n\n\n

\nConclusion: staying ahead in the AI arms race<\/h2>\n\n\n\n

The battle against deepfakes is a race against time and against rapidly evolving technology. Every breakthrough in generative AI demands an equally innovative defence strategy. \u201cAs AI evolves, so must our defences,\u201d says Ghorbel. \u201cResearch like ours is essential to ensure the safety and trustworthiness of our digital world.\u201d<\/p>\n\n\n\n

By pushing the boundaries of AI-driven detection, researchers help build a future where digital deception no longer poses an unchecked threat. Their work helps us tell fact from fiction in our digital world. This keeps trust at the heart of our tech future.<\/p>\n\n\n\n

—<\/p>\n\n\n\n

Computer Vision, Imaging and Machine Intelligence<\/strong> (CVI2<\/a>) conducts research in real-world applications of computer vision, image analysis, and machine intelligence, with extensive development of AI approaches. The expertise of CVI2 spans all stages of computer vision, including acquisition, processing, analysis, and decision.<\/p>\n\n\n\n

Who’s real?<\/strong> Did you figure out which photograph, left or right, is a deepfake? It’s the one on the left!<\/p>\n\n\n

\n \n

\nPeople in this story<\/h2>\n
    \n
  • \n
    \n
    \n
    \n \n\"Assoc.\n <\/figure>\n <\/div>\n
    \n

    Assoc. Prof Djamila AOUADA<\/h3>\n

    Deputy Director of SNT, Associate professor in Computer Vision<\/p>\n

    \n \n \n Learn more<\/span>\n <\/span>\n <\/use><\/svg> <\/a>\n<\/div>\n <\/div>\n <\/div>\n<\/div>\n<\/div><\/li>
  • \n
    \n
    \n
    \n \n\"Dr.\n <\/figure>\n <\/div>\n
    \n

    Dr. Anis KACEM<\/h3>\n

    Research scientist<\/p>\n

    \n \n \n Learn more<\/span>\n <\/span>\n <\/use><\/svg> <\/a>\n<\/div>\n <\/div>\n <\/div>\n<\/div>\n<\/div><\/li>
  • \n
    \n
    \n
    \n \n\"Van\n <\/figure>\n <\/div>\n
    \n

    Van Dat NGUYEN<\/h3>\n

    Research and development specialist<\/p>\n

    \n \n \n Learn more<\/span>\n <\/span>\n <\/use><\/svg> <\/a>\n<\/div>\n <\/div>\n <\/div>\n<\/div>\n<\/div><\/li>
  • \n
    \n
    \n
    \n \n\"Dr.\n <\/figure>\n <\/div>\n
    \n

    Dr. Nesryne MEJRI<\/h3>\n

    Postdoctoral researcher<\/p>\n

    \n \n \n Learn more<\/span>\n <\/span>\n <\/use><\/svg> <\/a>\n<\/div>\n <\/div>\n <\/div>\n<\/div>\n<\/div><\/li>
  • \n
    \n \n
    \n
    \n \n\"\"\n <\/figure><\/div>\n\n\n\n
    \n

    \nMarcella Astrid<\/h3>\n\n\n\n

    AI consultant<\/p>\n\n

    \n \n \n View profile<\/span>\n <\/span>\n <\/use><\/svg> <\/a>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n\n<\/li>
  • \n
    \n \n
    \n
    \n \n\"\"\n <\/figure><\/div>\n\n\n\n
    \n

    \nNiki Foteinopoulou<\/h3>\n\n\n\n

    Research scientist<\/p>\n\n

    \n \n \n View profile<\/span>\n <\/span>\n <\/use><\/svg> <\/a>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n\n<\/li><\/ul>\n\n<\/div>\n\n<\/div><\/section>\n","protected":false},"excerpt":{"rendered":"

    Every five minutes, somewhere in the world, someone creates a new deepfake. As this AI-powered threat grows, researchers are developing equally powerful tools to fight back.<\/p>\n","protected":false},"author":326,"featured_media":15351,"template":"","format":"standard","meta":{"featured_image_focal_point":[],"show_featured_caption":false,"ulux_newsletter_groups":"","uluxPostTitle":"","uluxPrePostTitle":"","_trash_the_other_posts":false,"_price":"","_stock":"","_tribe_ticket_header":"","_tribe_default_ticket_provider":"","_tribe_ticket_capacity":"0","_ticket_start_date":"","_ticket_end_date":"","_tribe_ticket_show_description":"","_tribe_ticket_show_not_going":false,"_tribe_ticket_use_global_stock":"","_tribe_ticket_global_stock_level":"","_global_stock_mode":"","_global_stock_cap":"","_tribe_rsvp_for_event":"","_tribe_ticket_going_count":"","_tribe_ticket_not_going_count":"","_tribe_tickets_list":"[]","_tribe_ticket_has_attendee_info_fields":false},"news-category":[4],"news-topic":[10],"organisation":[187,184],"authorship":[326],"acf":[],"yoast_head":"\nA race against deepfakes: how AI is fighting AI - SnT news I University of Luxembourg<\/title>\n<meta name=\"description\" content=\"Every five minutes, somewhere in the world, someone creates a new deepfake. As this AI-powered threat grows, researchers are developing equally powerful tools to fight back. Deepfake is a growing AI-powered threat and researchers are developing equally powerful tools to fight back.\" \/>\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.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/\" \/>\n<meta property=\"og:locale\" content=\"en_GB\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"A race against deepfakes: how AI is fighting AI\" \/>\n<meta property=\"og:description\" content=\"Every five minutes, somewhere in the world, someone creates a new deepfake. As this AI-powered threat grows, researchers are developing equally powerful tools to fight back.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/\" \/>\n<meta property=\"og:site_name\" content=\"SnT EN\" \/>\n<meta property=\"article:modified_time\" content=\"2025-12-11T16:14:28+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.uni.lu\/wp-content\/uploads\/sites\/5\/2025\/03\/Deepfake-AdopeStock-WIS.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1024\" \/>\n\t<meta property=\"og:image:height\" content=\"768\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Estimated reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/\"},\"author\":{\"name\":\"Geeta\",\"@id\":\"https:\/\/www.uni.lu\/snt-en\/#\/schema\/person\/7f5186b4d6fc7de90b6fe3fc98f170ce\"},\"headline\":\"A race against deepfakes: how AI is fighting AI\",\"datePublished\":\"2025-03-25T09:36:56+00:00\",\"dateModified\":\"2025-12-11T16:14:28+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/\"},\"wordCount\":1008,\"publisher\":{\"@id\":\"https:\/\/www.uni.lu\/snt-en\/#organization\"},\"image\":{\"@id\":\"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.uni.lu\/wp-content\/uploads\/sites\/5\/2025\/03\/Deepfake-AdopeStock-WIS.jpg\",\"inLanguage\":\"en-GB\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/\",\"url\":\"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/\",\"name\":\"A race against deepfakes: how AI is fighting AI - SnT news I University of Luxembourg\",\"isPartOf\":{\"@id\":\"https:\/\/www.uni.lu\/snt-en\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.uni.lu\/wp-content\/uploads\/sites\/5\/2025\/03\/Deepfake-AdopeStock-WIS.jpg\",\"datePublished\":\"2025-03-25T09:36:56+00:00\",\"dateModified\":\"2025-12-11T16:14:28+00:00\",\"description\":\"Every five minutes, somewhere in the world, someone creates a new deepfake. As this AI-powered threat grows, researchers are developing equally powerful tools to fight back. Deepfake is a growing AI-powered threat and researchers are developing equally powerful tools to fight back.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/#breadcrumb\"},\"inLanguage\":\"en-GB\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/#primaryimage\",\"url\":\"https:\/\/www.uni.lu\/wp-content\/uploads\/sites\/5\/2025\/03\/Deepfake-AdopeStock-WIS.jpg\",\"contentUrl\":\"https:\/\/www.uni.lu\/wp-content\/uploads\/sites\/5\/2025\/03\/Deepfake-AdopeStock-WIS.jpg\",\"width\":1024,\"height\":768,\"caption\":\"Picture: AdobeStock\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.uni.lu\/en\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Interdisciplinary Centre for Security, Reliability and Trust (SnT)\",\"item\":\"https:\/\/www.uni.lu\/snt-en\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"News\",\"item\":\"https:\/\/www.uni.lu\/snt-en\/news\/\"},{\"@type\":\"ListItem\",\"position\":4,\"name\":\"A race against deepfakes: how AI is fighting AI\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.uni.lu\/snt-en\/#website\",\"url\":\"https:\/\/www.uni.lu\/snt-en\/\",\"name\":\"SnT\",\"description\":\"Interdisciplinary Centre for Security, Reliability and Trust I Uni.lu\",\"publisher\":{\"@id\":\"https:\/\/www.uni.lu\/snt-en\/#organization\"},\"alternateName\":\"Interdisciplinary Centre for Security, Reliability and Trust I University of Luxembourg\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.uni.lu\/snt-en\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-GB\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.uni.lu\/snt-en\/#organization\",\"name\":\"SnT - University of Luxembourg I Uni.lu\",\"alternateName\":\"Interdisciplinary Centre for Security, Reliability and Trust\",\"url\":\"https:\/\/www.uni.lu\/snt-en\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/www.uni.lu\/snt-en\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.uni.lu\/wp-content\/uploads\/sites\/5\/2026\/03\/03112604\/SNT_SM-Profile_1600x1600px-scaled.jpg\",\"contentUrl\":\"https:\/\/www.uni.lu\/wp-content\/uploads\/sites\/5\/2026\/03\/03112604\/SNT_SM-Profile_1600x1600px-scaled.jpg\",\"width\":2560,\"height\":2560,\"caption\":\"SnT - University of Luxembourg I Uni.lu\"},\"image\":{\"@id\":\"https:\/\/www.uni.lu\/snt-en\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.linkedin.com\/school\/snt-lu\/\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.uni.lu\/snt-en\/#\/schema\/person\/7f5186b4d6fc7de90b6fe3fc98f170ce\",\"name\":\"Geeta\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-GB\",\"@id\":\"https:\/\/www.uni.lu\/snt-en\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/1e2ee5c3efd624acfb14f7cd04d93d50?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/1e2ee5c3efd624acfb14f7cd04d93d50?s=96&d=mm&r=g\",\"caption\":\"Geeta\"}}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"A race against deepfakes: how AI is fighting AI - SnT news I University of Luxembourg","description":"Every five minutes, somewhere in the world, someone creates a new deepfake. As this AI-powered threat grows, researchers are developing equally powerful tools to fight back. Deepfake is a growing AI-powered threat and researchers are developing equally powerful tools to fight back.","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.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/","og_locale":"en_GB","og_type":"article","og_title":"A race against deepfakes: how AI is fighting AI","og_description":"Every five minutes, somewhere in the world, someone creates a new deepfake. As this AI-powered threat grows, researchers are developing equally powerful tools to fight back.","og_url":"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/","og_site_name":"SnT EN","article_modified_time":"2025-12-11T16:14:28+00:00","og_image":[{"width":1024,"height":768,"url":"https:\/\/www.uni.lu\/wp-content\/uploads\/sites\/5\/2025\/03\/Deepfake-AdopeStock-WIS.jpg","type":"image\/jpeg"}],"twitter_card":"summary_large_image","twitter_misc":{"Estimated reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/#article","isPartOf":{"@id":"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/"},"author":{"name":"Geeta","@id":"https:\/\/www.uni.lu\/snt-en\/#\/schema\/person\/7f5186b4d6fc7de90b6fe3fc98f170ce"},"headline":"A race against deepfakes: how AI is fighting AI","datePublished":"2025-03-25T09:36:56+00:00","dateModified":"2025-12-11T16:14:28+00:00","mainEntityOfPage":{"@id":"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/"},"wordCount":1008,"publisher":{"@id":"https:\/\/www.uni.lu\/snt-en\/#organization"},"image":{"@id":"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/#primaryimage"},"thumbnailUrl":"https:\/\/www.uni.lu\/wp-content\/uploads\/sites\/5\/2025\/03\/Deepfake-AdopeStock-WIS.jpg","inLanguage":"en-GB"},{"@type":"WebPage","@id":"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/","url":"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/","name":"A race against deepfakes: how AI is fighting AI - SnT news I University of Luxembourg","isPartOf":{"@id":"https:\/\/www.uni.lu\/snt-en\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/#primaryimage"},"image":{"@id":"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/#primaryimage"},"thumbnailUrl":"https:\/\/www.uni.lu\/wp-content\/uploads\/sites\/5\/2025\/03\/Deepfake-AdopeStock-WIS.jpg","datePublished":"2025-03-25T09:36:56+00:00","dateModified":"2025-12-11T16:14:28+00:00","description":"Every five minutes, somewhere in the world, someone creates a new deepfake. As this AI-powered threat grows, researchers are developing equally powerful tools to fight back. Deepfake is a growing AI-powered threat and researchers are developing equally powerful tools to fight back.","breadcrumb":{"@id":"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/#breadcrumb"},"inLanguage":"en-GB","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/"]}]},{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/#primaryimage","url":"https:\/\/www.uni.lu\/wp-content\/uploads\/sites\/5\/2025\/03\/Deepfake-AdopeStock-WIS.jpg","contentUrl":"https:\/\/www.uni.lu\/wp-content\/uploads\/sites\/5\/2025\/03\/Deepfake-AdopeStock-WIS.jpg","width":1024,"height":768,"caption":"Picture: AdobeStock"},{"@type":"BreadcrumbList","@id":"https:\/\/www.uni.lu\/snt-en\/news\/a-race-against-deepfakes\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.uni.lu\/en"},{"@type":"ListItem","position":2,"name":"Interdisciplinary Centre for Security, Reliability and Trust (SnT)","item":"https:\/\/www.uni.lu\/snt-en\/"},{"@type":"ListItem","position":3,"name":"News","item":"https:\/\/www.uni.lu\/snt-en\/news\/"},{"@type":"ListItem","position":4,"name":"A race against deepfakes: how AI is fighting AI"}]},{"@type":"WebSite","@id":"https:\/\/www.uni.lu\/snt-en\/#website","url":"https:\/\/www.uni.lu\/snt-en\/","name":"SnT","description":"Interdisciplinary Centre for Security, Reliability and Trust I Uni.lu","publisher":{"@id":"https:\/\/www.uni.lu\/snt-en\/#organization"},"alternateName":"Interdisciplinary Centre for Security, Reliability and Trust I University of Luxembourg","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.uni.lu\/snt-en\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-GB"},{"@type":"Organization","@id":"https:\/\/www.uni.lu\/snt-en\/#organization","name":"SnT - University of Luxembourg I Uni.lu","alternateName":"Interdisciplinary Centre for Security, Reliability and Trust","url":"https:\/\/www.uni.lu\/snt-en\/","logo":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/www.uni.lu\/snt-en\/#\/schema\/logo\/image\/","url":"https:\/\/www.uni.lu\/wp-content\/uploads\/sites\/5\/2026\/03\/03112604\/SNT_SM-Profile_1600x1600px-scaled.jpg","contentUrl":"https:\/\/www.uni.lu\/wp-content\/uploads\/sites\/5\/2026\/03\/03112604\/SNT_SM-Profile_1600x1600px-scaled.jpg","width":2560,"height":2560,"caption":"SnT - University of Luxembourg I Uni.lu"},"image":{"@id":"https:\/\/www.uni.lu\/snt-en\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.linkedin.com\/school\/snt-lu\/"]},{"@type":"Person","@id":"https:\/\/www.uni.lu\/snt-en\/#\/schema\/person\/7f5186b4d6fc7de90b6fe3fc98f170ce","name":"Geeta","image":{"@type":"ImageObject","inLanguage":"en-GB","@id":"https:\/\/www.uni.lu\/snt-en\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/1e2ee5c3efd624acfb14f7cd04d93d50?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/1e2ee5c3efd624acfb14f7cd04d93d50?s=96&d=mm&r=g","caption":"Geeta"}}]}},"blog_id":5,"_links":{"self":[{"href":"https:\/\/www.uni.lu\/snt-en\/wp-json\/wp\/v2\/news\/15349"}],"collection":[{"href":"https:\/\/www.uni.lu\/snt-en\/wp-json\/wp\/v2\/news"}],"about":[{"href":"https:\/\/www.uni.lu\/snt-en\/wp-json\/wp\/v2\/types\/news"}],"author":[{"embeddable":true,"href":"https:\/\/www.uni.lu\/snt-en\/wp-json\/wp\/v2\/users\/326"}],"version-history":[{"count":4,"href":"https:\/\/www.uni.lu\/snt-en\/wp-json\/wp\/v2\/news\/15349\/revisions"}],"predecessor-version":[{"id":19769,"href":"https:\/\/www.uni.lu\/snt-en\/wp-json\/wp\/v2\/news\/15349\/revisions\/19769"}],"wp:authorship":[{"embeddable":true,"href":"https:\/\/www.uni.lu\/snt-en\/wp-json\/wp\/v2\/users\/326"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.uni.lu\/snt-en\/wp-json\/wp\/v2\/media\/15351"}],"wp:attachment":[{"href":"https:\/\/www.uni.lu\/snt-en\/wp-json\/wp\/v2\/media?parent=15349"}],"wp:term":[{"taxonomy":"news-category","embeddable":true,"href":"https:\/\/www.uni.lu\/snt-en\/wp-json\/wp\/v2\/news-category?post=15349"},{"taxonomy":"news-topic","embeddable":true,"href":"https:\/\/www.uni.lu\/snt-en\/wp-json\/wp\/v2\/news-topic?post=15349"},{"taxonomy":"organisation","embeddable":true,"href":"https:\/\/www.uni.lu\/snt-en\/wp-json\/wp\/v2\/organisation?post=15349"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}