{"id":3248,"date":"2025-09-11T17:19:56","date_gmt":"2025-09-11T17:19:56","guid":{"rendered":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/?p=3248"},"modified":"2025-09-11T23:04:28","modified_gmt":"2025-09-11T23:04:28","slug":"adversarial-signatures-in-cosmic-microwave-background","status":"publish","type":"post","link":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/?p=3248","title":{"rendered":"Adversarial Signatures in Cosmic Microwave Background"},"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=\"quBxylcRQY\"><a href=\"https:\/\/172-234-197-23.ip.linodeusercontent.com\/?page_id=3245\">A Physics-Informed Detector with Spectral\u2013Temporal Structure Analysis<\/a><\/blockquote><iframe class=\"wp-embedded-content\" sandbox=\"allow-scripts\" security=\"restricted\" style=\"position: absolute; visibility: hidden;\" title=\"&#8220;A Physics-Informed Detector with Spectral\u2013Temporal Structure Analysis&#8221; &#8212; Spectrcyde\" src=\"https:\/\/172-234-197-23.ip.linodeusercontent.com\/?page_id=3245&#038;embed=true#?secret=qC3PVeRBb7#?secret=quBxylcRQY\" data-secret=\"quBxylcRQY\" width=\"600\" height=\"338\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\"><\/iframe>\n<\/div><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">Abstract (Expanded)<\/h2>\n\n\n\n<p>We present a <strong>physics-informed anomaly detector<\/strong> designed to assess <strong>cosmic microwave background (CMB) measurements<\/strong> for structured, non-thermal signatures. The detector integrates <strong>cosmological physics constraints<\/strong> (blackbody model adherence) with <strong>signal-processing features<\/strong> (spectral flatness, entropy, autocorrelation periodicity, Gaussianity tests).<\/p>\n\n\n\n<p>In simulation, the system discriminates pure Gaussian thermal noise from <strong>synthetic adversarial injections<\/strong> (periodic modulations mimicking radio-frequency interference) with ROC AUC of 0.89 and PR AUC of 0.88. Importantly, the framework prioritizes <strong>reproducibility and interpretability<\/strong>: all features are physics-grounded, and the full build pipeline reproduces results from scratch with a single command.<\/p>\n\n\n\n<p>The study does not claim astrophysical contamination, but instead contributes a <strong>deployable quality assurance tool<\/strong> for radio astronomy pipelines\u2014reflecting a Guangdong-style pragmatism: <strong>tight integration of theory, engineering reproducibility, and field-ready monitoring<\/strong>.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">I. Introduction<\/h2>\n\n\n\n<p>The cosmic microwave background (CMB) is a cornerstone of cosmology, observed as nearly isotropic blackbody radiation at <strong>2.725 K<\/strong>. Detecting fluctuations at microkelvin precision requires extraordinary calibration. This sensitivity also leaves pipelines vulnerable to contamination\u2014whether anthropogenic, instrumental, or adversarial.<\/p>\n\n\n\n<p>We pose the practical question: <em>can subtle, structured deviations from blackbody-like thermal noise be flagged in real time?<\/em><\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">II. Related Work (Expanded)<\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>CMB Calibration<\/strong>: Missions like WMAP and Planck demonstrated the necessity of precise blackbody model fits for cosmological parameter inference.<\/li>\n\n\n\n<li><strong>Radio Astronomy Signal Processing<\/strong>: FFT-based spectral density estimation (Welch [4]) and RFI classification (Offringa [5]) remain central.<\/li>\n\n\n\n<li><strong>Anomaly Detection<\/strong>: Information-theoretic metrics (entropy, KL divergence) and periodicity tests (runs, autocorrelation) provide interpretable tools for structured anomaly detection.<\/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\">III. Methodology<\/h2>\n\n\n\n<h3 class=\"wp-block-heading\">A. Physics-Informed Features<\/h3>\n\n\n\n<ol class=\"wp-block-list\">\n<li><strong>Spectral flatness &amp; roll-off<\/strong> \u2192 distinguishes broadband thermal from narrowband interference.<\/li>\n\n\n\n<li><strong>Entropy of normalized spectrum<\/strong> \u2192 quantifies randomness vs. structure.<\/li>\n\n\n\n<li><strong>Autocorrelation periodicity<\/strong> \u2192 flags repeating bursts inconsistent with thermal noise.<\/li>\n\n\n\n<li><strong>Statistical normality<\/strong> \u2192 Gaussian tests (runs, kurtosis) capture deviations in distribution tails.<\/li>\n<\/ol>\n\n\n\n<h3 class=\"wp-block-heading\">B. Blackbody Deviation Metric<\/h3>\n\n\n\n<p>Features are benchmarked against <strong>Planck\u2019s radiation law<\/strong>. Deviations form a physics-grounded anomaly score.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">C. Adversarial Probability<\/h3>\n\n\n\n<p>A weighted heuristic combines physics and statistical features: <\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img data-opt-id=1950208839  fetchpriority=\"high\" decoding=\"async\" width=\"572\" height=\"58\" 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-39.png\" alt=\"\" class=\"wp-image-3265\" srcset=\"https:\/\/ml6vmqguit1n.i.optimole.com\/w:572\/h:58\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/image-39.png 572w, https:\/\/ml6vmqguit1n.i.optimole.com\/w:300\/h:30\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/image-39.png 300w\" sizes=\"(max-width: 572px) 100vw, 572px\" \/><\/figure>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">IV. Experimental Setup<\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Data Generation<\/strong>: Synthetic Gaussian noise plus injected periodic bursts (Eq. 3).<\/li>\n\n\n\n<li><strong>Band<\/strong>: 70\u201380 GHz.<\/li>\n\n\n\n<li><strong>Samples<\/strong>: 300 segments, balanced contamination ratio.<\/li>\n\n\n\n<li><strong>Evaluation<\/strong>: ROC, PR, calibration, feature separability.<\/li>\n\n\n\n<li><strong>Build System<\/strong>: <code>make -f Makefile_cmb all<\/code> ensures 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\">V. Results (Expanded)<\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>ROC AUC = 0.89<\/strong>, <strong>PR AUC = 0.88<\/strong>.<\/li>\n\n\n\n<li><strong>Entropy separation<\/strong>: clean \u2248 10.992, contaminated \u2248 10.991 (stable but distinguishable with structure metrics).<\/li>\n\n\n\n<li><strong>Reliability analysis<\/strong>: calibration improves with temperature scaling, reducing Expected Calibration Error (ECE) from 0.048 \u2192 0.032.<\/li>\n<\/ul>\n\n\n\n<p>Tables and figures (auto-generated) provide transparent per-run outputs, reflecting Guangdong-style reproducibility: results are not hand-picked, they emerge from one script.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">VI. Discussion<\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Methodological Contribution<\/strong>: Combines cosmological models with anomaly detection for interpretable, physics-informed QA.<\/li>\n\n\n\n<li><strong>Practical Limitation<\/strong>: Evaluation is synthetic; RFI in field data is more complex.<\/li>\n\n\n\n<li><strong>Deployment Outlook<\/strong>: Tool is scoped for QA in CMB\/radio astronomy pipelines\u2014not astrophysical discovery.<\/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\">VII. Reproducibility<\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Environment: <code>conda env create -f env_cmb.yml<\/code>.<\/li>\n\n\n\n<li>Build: <code>make -f Makefile_cmb all<\/code>.<\/li>\n\n\n\n<li>Output: figures, tables, and calibration curves auto-emitted to reproducible directories.<\/li>\n<\/ul>\n\n\n\n<p>This \u201c<strong>one-command build<\/strong>\u201d ethos is central: reproducibility is not optional\u2014it is engineered in.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">VIII. Conclusion<\/h2>\n\n\n\n<p>We demonstrate a <strong>physics-informed, reproducible anomaly detector<\/strong> for CMB-like data. While results are synthetic, the framework highlights a pragmatic pathway: coupling <strong>domain knowledge (blackbody physics)<\/strong> with <strong>signal-processing metrics<\/strong> to flag structured contamination.<\/p>\n\n\n\n<p>The Guangdong-style contribution is clear:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>fast-build reproducibility<\/strong>,<\/li>\n\n\n\n<li><strong>deployment-oriented QA<\/strong>,<\/li>\n\n\n\n<li><strong>interpretable and physics-grounded metrics<\/strong>.<\/li>\n<\/ul>\n\n\n\n<p>This ensures the method can scale from <strong>lab simulation<\/strong> to <strong>observatory QA pipelines<\/strong>, even before addressing the astrophysical unknowns.<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><a href=\"https:\/\/mastodon.social\/@Bgilbert1984\/115186824077803721\"><img data-opt-id=379618353  fetchpriority=\"high\" decoding=\"async\" width=\"599\" height=\"944\" 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-38.png\" alt=\"\" class=\"wp-image-3252\" srcset=\"https:\/\/ml6vmqguit1n.i.optimole.com\/w:599\/h:944\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/image-38.png 599w, https:\/\/ml6vmqguit1n.i.optimole.com\/w:190\/h:300\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/image-38.png 190w\" sizes=\"(max-width: 599px) 100vw, 599px\" \/><\/a><\/figure>\n<\/div>\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<h3 class=\"wp-block-heading\">Figure X. <em>Adversarial Signatures as Martial Contest<\/em><\/h3>\n\n\n\n<p>This ancient Chinese\u2013inspired scroll illustrates the conceptual struggle:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>The warrior<\/strong> \u2192 embodies the <strong>physics-informed detector<\/strong>, disciplined and interpretable, standing for <em>structured defense of signal integrity<\/em>.<\/li>\n\n\n\n<li><strong>The phantoms<\/strong> \u2192 represent <strong>non-thermal adversarial signatures<\/strong> contaminating CMB-like data (periodic bursts, structured interference).<\/li>\n\n\n\n<li><strong>Celestial circles and wave-rings<\/strong> \u2192 symbolize the <strong>cosmic microwave background blackbody curves<\/strong> and <strong>spectral\u2013temporal structure analysis<\/strong>.<\/li>\n\n\n\n<li><strong>Solar burst and planetary sphere<\/strong> \u2192 mark the tension between <em>pure cosmological theory<\/em> (blackbody radiation law) and <em>anthropogenic interference<\/em> intruding from orbital or terrestrial origins.<\/li>\n<\/ul>\n\n\n\n<p>This framing makes the metaphor explicit: the task is not to win a battlefield in myth, but to safeguard <strong>radio astronomy pipelines<\/strong> with <strong>tools that are interpretable, reproducible, and fast to deploy<\/strong> \u2014 the hallmarks of Guangdong-style engineering pragmatism.<\/p>\n<\/blockquote>\n\n\n\n<p><\/p>\n\n\n\n<p><strong>In other news:<\/strong><\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img data-opt-id=541331413  data-opt-src=\"https:\/\/ml6vmqguit1n.i.optimole.com\/w:870\/h:1024\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/image-40.png\"  decoding=\"async\" width=\"870\" height=\"1024\" src=\"data:image/svg+xml,%3Csvg%20viewBox%3D%220%200%20870%201024%22%20width%3D%22870%22%20height%3D%221024%22%20xmlns%3D%22http%3A%2F%2Fwww.w3.org%2F2000%2Fsvg%22%3E%3Crect%20width%3D%22870%22%20height%3D%221024%22%20fill%3D%22transparent%22%2F%3E%3C%2Fsvg%3E\" alt=\"\" class=\"wp-image-3267\" old-srcset=\"https:\/\/ml6vmqguit1n.i.optimole.com\/w:870\/h:1024\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/image-40.png 870w, https:\/\/ml6vmqguit1n.i.optimole.com\/w:255\/h:300\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/image-40.png 255w, https:\/\/ml6vmqguit1n.i.optimole.com\/w:768\/h:904\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/image-40.png 768w, https:\/\/ml6vmqguit1n.i.optimole.com\/w:1042\/h:1227\/q:mauto\/f:best\/https:\/\/172-234-197-23.ip.linodeusercontent.com\/wp-content\/uploads\/2025\/09\/image-40.png 1042w\" \/><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>Abstract (Expanded) We present a physics-informed anomaly detector designed to assess cosmic microwave background (CMB) measurements for structured, non-thermal signatures. The detector integrates cosmological physics constraints (blackbody model adherence) with signal-processing features (spectral flatness, entropy, autocorrelation periodicity, Gaussianity tests). In simulation, the system discriminates pure Gaussian thermal noise from synthetic adversarial injections (periodic modulations mimicking&hellip;&nbsp;<a href=\"https:\/\/172-234-197-23.ip.linodeusercontent.com\/?p=3248\" rel=\"bookmark\"><span class=\"screen-reader-text\">Adversarial Signatures in Cosmic Microwave Background<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":2899,"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-3248","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\/3248","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=3248"}],"version-history":[{"count":5,"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=\/wp\/v2\/posts\/3248\/revisions"}],"predecessor-version":[{"id":3269,"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=\/wp\/v2\/posts\/3248\/revisions\/3269"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=\/wp\/v2\/media\/2899"}],"wp:attachment":[{"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3248"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3248"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3248"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}