{"id":3379,"date":"2025-09-13T17:16:48","date_gmt":"2025-09-13T17:16:48","guid":{"rendered":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/?p=3379"},"modified":"2025-09-13T17:18:45","modified_gmt":"2025-09-13T17:18:45","slug":"ndpi-rf-fusion-for-algorithmic-manipulation-detection","status":"publish","type":"post","link":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/?p=3379","title":{"rendered":"nDPI\u2013RF Fusion for Algorithmic Manipulation Detection"},"content":{"rendered":"\n<figure class=\"wp-block-embed is-type-wp-embed is-provider-spectrcyde wp-block-embed-spectrcyde\"><div class=\"wp-block-embed__wrapper\">\n<blockquote class=\"wp-embedded-content\" data-secret=\"CSHkARmmGy\"><a href=\"https:\/\/172-234-197-23.ip.linodeusercontent.com\/?page_id=3374\">nDPI\u2013RF Fusion for Algorithmic Manipulation Detection<\/a><\/blockquote><iframe class=\"wp-embedded-content\" sandbox=\"allow-scripts\" security=\"restricted\" style=\"position: absolute; visibility: hidden;\" title=\"&#8220;nDPI\u2013RF Fusion for Algorithmic Manipulation Detection&#8221; &#8212; Spectrcyde\" src=\"https:\/\/172-234-197-23.ip.linodeusercontent.com\/?page_id=3374&#038;embed=true#?secret=dLZW4O0d8d#?secret=CSHkARmmGy\" data-secret=\"CSHkARmmGy\" width=\"600\" height=\"338\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"><\/iframe>\n<\/div><\/figure>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-large\"><a href=\"https:\/\/www.facebook.com\/share\/p\/1BBptW92SJ\/\"><img data-opt-id=1957162142  fetchpriority=\"high\" decoding=\"async\" width=\"915\" height=\"1024\" src=\"https:\/\/ml6vmqguit1n.i.optimole.com\/w:915\/h:1024\/q:mauto\/f:best\/http:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/image-41.png\" alt=\"\" class=\"wp-image-3272\" srcset=\"https:\/\/ml6vmqguit1n.i.optimole.com\/w:915\/h:1024\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/image-41.png 915w, https:\/\/ml6vmqguit1n.i.optimole.com\/w:268\/h:300\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/image-41.png 268w, https:\/\/ml6vmqguit1n.i.optimole.com\/w:768\/h:860\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/image-41.png 768w, https:\/\/ml6vmqguit1n.i.optimole.com\/w:972\/h:1088\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/image-41.png 972w\" sizes=\"(max-width: 915px) 100vw, 915px\" \/><\/a><\/figure>\n<\/div>\n\n\n<p><em>\u201cnDPI\u2013RF Fusion for Algorithmic Manipulation Detection\u201d<\/em><\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h1 class=\"wp-block-heading\">Detecting Algorithmic Manipulation with nDPI\u2013RF Fusion<\/h1>\n\n\n\n<p><em>By Benjamin J. Gilbert, College of the Mainland \u2013 Robotic Process Automation | Spectrcyde RF Quantum SCYTHE<\/em><\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Why Algorithmic Manipulation Detection Matters<\/h2>\n\n\n\n<p>As networks grow more complex and adversaries more subtle, manipulation can slip through traditional defenses. RF-only methods catch signal anomalies but miss higher-layer context. Deep Packet Inspection (DPI) shines at protocol analysis but is blind to the physical quirks of radio. The result? Blind spots that attackers exploit.<\/p>\n\n\n\n<p>That\u2019s where <strong>fusion<\/strong> comes in.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Our Approach: RF + nDPI<\/h2>\n\n\n\n<p>We\u2019ve built a reproducible pipeline that blends:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>RF features<\/strong> (SNR, burstiness, asymmetry, narrowband flags)<\/li>\n\n\n\n<li><strong>nDPI features<\/strong> (protocol histograms, entropy, suspicious traffic ratios)<\/li>\n\n\n\n<li><strong>Logistic regression fusion<\/strong> to bring the two together<\/li>\n\n\n\n<li><strong>Calibration via temperature scaling<\/strong>, ensuring trustworthy risk scores<\/li>\n<\/ul>\n\n\n\n<p>The pipeline is scripted end-to-end for repeatability, shipping with JSON\u2192TeX automation so figures and tables generate seamlessly for publication.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Experimental Setup<\/h2>\n\n\n\n<p>We stress-tested the system under controlled conditions:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>SNR range:<\/strong> \u221210 dB to +20 dB<\/li>\n\n\n\n<li><strong>Blockers:<\/strong> random injections<\/li>\n\n\n\n<li><strong>Traffic:<\/strong> realistic protocol mixes with suspicious ratios<\/li>\n\n\n\n<li><strong>Samples:<\/strong> 2000 per configuration<\/li>\n\n\n\n<li><strong>Hardware:<\/strong> CPU-only benchmark for transparency and reproducibility<\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">What We Found<\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Fusion improves accuracy.<\/strong> Across all SNR conditions, RF+DPI outperformed RF-only detection. At 0 dB SNR, F1 jumped from <strong>0.613 \u2192 0.638<\/strong>.<\/li>\n\n\n\n<li><strong>Risk scores are reliable.<\/strong> Temperature scaling cut Expected Calibration Error (ECE), making outputs more trustworthy in live operations.<\/li>\n\n\n\n<li><strong>Protocol diversity matters.<\/strong> Even when RF degraded, protocol histograms from nDPI helped anchor detection.<\/li>\n<\/ul>\n\n\n\n<p>Figures show the improvements clearly:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><em>F1 vs. SNR plots<\/em> confirm consistent fusion benefits.<\/li>\n\n\n\n<li><em>Protocol histograms<\/em> highlight TLS\/QUIC dominance in traffic.<\/li>\n\n\n\n<li><em>Reliability diagrams<\/em> prove calibration success.<\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Limitations &amp; Future Work<\/h2>\n\n\n\n<p>This study is a <strong>CPU-only synthetic benchmark<\/strong>. While reproducible, real-world deployments will need:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Live nDPI streams<\/strong> instead of emulated traffic<\/li>\n\n\n\n<li><strong>GPU acceleration<\/strong> for real-time performance<\/li>\n\n\n\n<li><strong>Expanded threat models<\/strong> to capture adversarial evasion tactics<\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Why It Matters<\/h2>\n\n\n\n<p>This fusion isn\u2019t just an academic curiosity\u2014it\u2019s an operational upgrade. By uniting RF and DPI perspectives, we can build detectors that:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Catch manipulations even in noisy or adversarial environments<\/li>\n\n\n\n<li>Deliver calibrated, decision-ready risk scores<\/li>\n\n\n\n<li>Run on modest hardware for reproducibility and transparency<\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Closing Thoughts<\/h2>\n\n\n\n<p>The <strong>nDPI\u2013RF fusion pipeline<\/strong> shows that bridging physical-layer and network-layer signals makes manipulation detection stronger, more trustworthy, and reproducible. With GPU acceleration and live deployment, it could power the next generation of <strong>resilient cyber-RF defense systems<\/strong>.<\/p>\n\n\n\n<p>\ud83d\udc49 The project is reproducible (commit f2017942, seed 42) and ships a build with JSON\u2192TeX toolchain.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><img data-opt-id=2144593476  fetchpriority=\"high\" decoding=\"async\" width=\"562\" height=\"623\" src=\"https:\/\/ml6vmqguit1n.i.optimole.com\/w:auto\/h:auto\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/image-58.png\" alt=\"\" class=\"wp-image-3380\" srcset=\"https:\/\/ml6vmqguit1n.i.optimole.com\/w:562\/h:623\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/image-58.png 562w, https:\/\/ml6vmqguit1n.i.optimole.com\/w:271\/h:300\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/image-58.png 271w\" sizes=\"(max-width: 562px) 100vw, 562px\" \/><\/figure>\n<\/div>\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u201cnDPI\u2013RF Fusion for Algorithmic Manipulation Detection\u201d Detecting Algorithmic Manipulation with nDPI\u2013RF Fusion By Benjamin J. Gilbert, College of the Mainland \u2013 Robotic Process Automation | Spectrcyde RF Quantum SCYTHE Why Algorithmic Manipulation Detection Matters As networks grow more complex and adversaries more subtle, manipulation can slip through traditional defenses. RF-only methods catch signal anomalies but&hellip;&nbsp;<a href=\"https:\/\/172-234-197-23.ip.linodeusercontent.com\/?p=3379\" rel=\"bookmark\"><span class=\"screen-reader-text\">nDPI\u2013RF Fusion for Algorithmic Manipulation Detection<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":3380,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"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":[10],"tags":[],"class_list":["post-3379","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-signal_scythe"],"_links":{"self":[{"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=\/wp\/v2\/posts\/3379","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=3379"}],"version-history":[{"count":2,"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=\/wp\/v2\/posts\/3379\/revisions"}],"predecessor-version":[{"id":3382,"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=\/wp\/v2\/posts\/3379\/revisions\/3382"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=\/wp\/v2\/media\/3380"}],"wp:attachment":[{"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3379"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3379"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3379"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}