{"id":8581,"date":"2022-10-18T12:39:00","date_gmt":"2022-10-18T10:39:00","guid":{"rendered":"https:\/\/sites.unica.it\/pralab\/?p=8581"},"modified":"2023-08-04T12:40:53","modified_gmt":"2023-08-04T10:40:53","slug":"tensor-based-deepfake-detection-in-scaled-and-compressed-images","status":"publish","type":"post","link":"https:\/\/sites.unica.it\/pralab\/2022\/10\/18\/tensor-based-deepfake-detection-in-scaled-and-compressed-images\/","title":{"rendered":"Tensor-Based Deepfake Detection in Scaled and Compressed Images"},"content":{"rendered":"\n<h6 class=\"wp-block-heading\">Abstract<\/h6>\n\n\n\n<p class=\"has-text-align-left is-style-info has-neve-text-color-color has-nv-site-bg-background-color has-text-color has-background\">When deepfakes are widespread on chatting platforms, they are expected to be subject to heavy resizing and compressing steps. In this paper, we present a tensor-based representation of compressed and resized images. Tensor embeds DCT features computed on multi-scaled and multi-compressed versions of the input facial image. Moreover, a custom deep-architecture is designed and trained on the proposed representation. Experimental results show its pros and cons with respect to state-of-the-art methods.<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p><strong>AUTHORS<\/strong> <a href=\"https:\/\/sites.unica.it\/pralab\/people\/sara-concas\/\" data-type=\"page\" data-id=\"7392\">Sara Concas<\/a>;\u00a0<a href=\"https:\/\/sites.unica.it\/pralab\/people\/gianpaolo-perelli\/\" data-type=\"page\" data-id=\"7776\">Gianpaolo Perelli<\/a>;\u00a0<a href=\"https:\/\/sites.unica.it\/pralab\/people\/gian-luca-marcialis\/\" data-type=\"page\" data-id=\"7284\">Gian Luca Marcialis<\/a>;\u00a0<a href=\"https:\/\/ieeexplore.ieee.org\/author\/37538247900\">Giovanni Puglisi<\/a><a rel=\"noreferrer noopener\" href=\"https:\/\/orcid.org\/0000-0003-4103-9190\" target=\"_blank\"><\/a><\/p>\n\n\n\n<p><strong>DOI<\/strong> <a rel=\"noreferrer noopener\" href=\"https:\/\/doi.org\/10.1109\/ICIP46576.2022.9897606\" target=\"_blank\">10.1109\/ICIP46576.2022.9897606<\/a><\/p>\n<cite><strong>Published in:\u00a0<\/strong><a href=\"https:\/\/ieeexplore.ieee.org\/xpl\/conhome\/9897158\/proceeding\">2022 IEEE International Conference on Image Processing (ICIP)<\/a><\/cite><\/blockquote>\n","protected":false},"excerpt":{"rendered":"<p>Abstract When deepfakes are widespread on chatting platforms, they are expected to be subject to heavy resizing and compressing steps. In this paper, we present a tensor-based representation of compressed and resized images. Tensor embeds DCT features computed on multi-scaled and multi-compressed versions of the input facial image. Moreover, a custom deep-architecture is designed and&hellip;&nbsp;<a href=\"https:\/\/sites.unica.it\/pralab\/2022\/10\/18\/tensor-based-deepfake-detection-in-scaled-and-compressed-images\/\" rel=\"bookmark\">Read More &raquo;<span class=\"screen-reader-text\">Tensor-Based Deepfake Detection in Scaled and Compressed Images<\/span><\/a><\/p>\n","protected":false},"author":3990,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_coblocks_attr":"","_coblocks_dimensions":"","_coblocks_responsive_height":"","_coblocks_accordion_ie_support":"","neve_meta_sidebar":"","neve_meta_container":"","neve_meta_enable_content_width":"","neve_meta_content_width":0,"neve_meta_title_alignment":"","neve_meta_author_avatar":"","neve_post_elements_order":"","neve_meta_disable_header":"","neve_meta_disable_footer":"","neve_meta_disable_title":"","footnotes":""},"categories":[26],"tags":[],"class_list":["post-8581","post","type-post","status-publish","format-standard","hentry","category-deepfake"],"_links":{"self":[{"href":"https:\/\/sites.unica.it\/pralab\/wp-json\/wp\/v2\/posts\/8581","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/sites.unica.it\/pralab\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/sites.unica.it\/pralab\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/sites.unica.it\/pralab\/wp-json\/wp\/v2\/users\/3990"}],"replies":[{"embeddable":true,"href":"https:\/\/sites.unica.it\/pralab\/wp-json\/wp\/v2\/comments?post=8581"}],"version-history":[{"count":2,"href":"https:\/\/sites.unica.it\/pralab\/wp-json\/wp\/v2\/posts\/8581\/revisions"}],"predecessor-version":[{"id":8804,"href":"https:\/\/sites.unica.it\/pralab\/wp-json\/wp\/v2\/posts\/8581\/revisions\/8804"}],"wp:attachment":[{"href":"https:\/\/sites.unica.it\/pralab\/wp-json\/wp\/v2\/media?parent=8581"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/sites.unica.it\/pralab\/wp-json\/wp\/v2\/categories?post=8581"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/sites.unica.it\/pralab\/wp-json\/wp\/v2\/tags?post=8581"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}