The new approach solves a long-standing obstacle to capturing digital video signals, which were considered too complex to reliably reconstruct due to their 10-bit encoding and nonlinear properties. The researchers therefore posed the problem as an inverse task and developed a deep learning model based on the DRUNet architecture. It converts electromagnetic signals back into a visual image. Another important advantage of the system is that it does not require complex physical measurements for each configuration, as it uses mathematical analysis and creates its own learning patterns.
Compared to older methods, which had an error rate of up to 90 percent, the new system reduces this to less than 30 percent. Despite significant progress, the results are far from perfect, as the reconstructed text still contains a significant amount of errors. This currently limits the possibility of direct malicious use in practice. The technology works with commonly available software-defined radio hardware and an extension for GNU Radio. The researchers have also made the source code and a database of approximately 7 gigabytes publicly available.
The discovery undoubtedly reopens the issue of screen security and electromagnetic data leakage. To reduce the risk, experts recommend using appropriate cables with better electromagnetic shielding, ferrite rings and specially certified housings. Ordinary cables and screens generally do not have the same level of protection against this type of interception.<\/p>","protected":false},"excerpt":{"rendered":"
Novi pristop re\u0161uje dolgoletno oviro prestrezanja digitalnih video signalov, ki so zaradi 10-bitnega kodiranja in svojih nelinearnih lastnosti veljali za preve\u010d zapletene za zanesljivo rekonstrukcijo. Raziskovalci so zato problem zastavili kot obratno nalogo in razvili model globokega u\u010denja, ki temelji na arhitekturi DRUNet. Ta elektromagnetne signale pretvarja nazaj v vizualno podobo. Pomembna prednost sistema je […]<\/p>","protected":false},"author":2,"featured_media":0,"comment_status":"","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[4],"tags":[192],"class_list":["post-8368","post","type-post","status-publish","format-standard","hentry","category-racunalnistvo-telefonija","tag-umetna-inteligenca"],"acf":{"subtitle":"Raziskovalci z univerze v Montevideu so razvili sistem Deep-TEMPEST, ki s pomo\u010djo umetne inteligence sestavi vsebino zaslona na podlagi elektromagnetnega sevanja kablov HDMI. Nova metoda sicer temelji na konceptu, znanem \u017ee iz \u010dasov analogne tehnologije VGA, vendar ga uspe\u0161no prena\u0161a tudi v digitalno okolje.","heading":"","summary":"Sistem Deep-TEMPEST omogo\u010da zajem besedila z zaslona prek elektromagnetnih emisij HDMI kablov s pomo\u010djo umetne inteligence, pri \u010demer stopnja napak ostaja pod 30 odstotki, re\u0161itev pa zahteva stro\u017ejo za\u0161\u010dito kablov.","thumbnail_small":"https:\/\/racunalniske-novice.com\/wp-content\/uploads\/2026\/11\/pexels-kampus-8353774-560x315.jpg","thumbnail_large":"https:\/\/racunalniske-novice.com\/wp-content\/uploads\/2026\/11\/pexels-kampus-8353774-1024x684.jpg","thumbnail_caption":"Foto: Pexels","gallery":"","video_gallery":null,"author":"","links":null,"sources":[{"title":"hwupgrade","url":"https:\/\/www.hwupgrade.it\/news\/sicurezza-software\/spiare-un-monitor-dal-cavo-hdmi-un-ia-azzecca-oltre-7-caratteri-su-10_161831.html"}],"skip_language":[]},"yoast_head":"\n