BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VEVENT DTSTAMP:20260416T183413Z UID:F3B4ABFD-95FE-419E-8DA9-7D5267A43E41 DTSTART;TZID=Etc/UTC:20260416T120000 DTEND;TZID=Etc/UTC:20260416T131500 DESCRIPTION:[6G-Bench: : Evaluating Semantic Communication and Network-Leve l Reasoning in AI-Native 6G Systems]\n\nSpecial Presentation by Mohamed Am ine Ferrag (UAE University\, UAE)\n\nHosted by the Future Networks Artific ial Intelligence & Machine Learning (AIML) Working Group\n\nDate/Time: Thu rsday\, 16 April 2026 @ 12:00 UTC (12 PM GMT)\n\nTopic:\n\n6G-Bench: Evalu ating Semantic Communication and Network-Level Reasoning in AI-Native 6G S ystems\n\nAbstract:\n\nEmerging sixth-generation (6G) networks are envisio ned as AI-native systems in which foundation models act as high-level reas oning and coordination layers above standardized network functions. While large language models (LLMs) have demonstrated strong capabilities in isol ated wireless and networking tasks\, their ability to perform network-leve l semantic reasoning over intents\, policies\, trust constraints\, and mul ti-agent coordination remains insufficiently evaluated.\n\nIn this talk\, I will present 6G-Bench\, an open benchmark designed to rigorously assess semantic communication and network-level reasoning in AI-native 6G environ ments. The benchmark defines a taxonomy of 30 decision-making tasks aligne d with ongoing standardization efforts in 3GPP\, IETF\, ETSI\, ITU-T\, and the O-RAN Alliance. These tasks are grouped into five capability categori es: intent and policy reasoning\, network slicing and resource management\ , trust and security awareness\, AI-native networking and agentic control\ , and distributed intelligence for emerging 6G use cases.\n\nStarting from over 113\,000 realistic 6G operational scenarios\, we construct 10\,000 v ery-hard\, task-conditioned multiple-choice questions that require multi-s tep quantitative reasoning under uncertainty and worst-case regret minimiz ation. After automated filtering and expert validation\, 3\,722 high-confi dence questions form the final evaluation set.\n\nI will also present a co mprehensive evaluation of 22 contemporary foundation models and discuss ke y insights for deploying AI reasoning layers in future AI-native 6G networ ks.\n\nSpeaker:\n\n[]\nMohamed Amine Ferrag earned his Bachelor’s\, Mast er’s\, Ph.D.\, and Habilitation degrees in Computer Science from Badji M okhtar—Annaba University\, Algeria\, in 2008\, 2010\, 2014\, and 2019\, respectively. He served as an Associate Professor at Guelma University\, A lgeria (2014–2022)\, and as a Senior Researcher at the NAU-Lincoln Joint Research Center for Intelligent Engineering\, Nanjing Agricultural Univer sity\, China (2019–2022). From 2022 to 2024\, he was Lead Researcher at the Technology Innovation Institute (TII)\, Abu Dhabi\, where he led AI-dr iven cybersecurity research initiatives. In 2025\, he joined the United Ar ab Emirates University (UAEU) as an Associate Professor in the Department of Computer and Network Engineering.\n\nHis research focuses on cybersecur ity and AI-native systems\, including wireless network security\, network coding security\, applied cryptography\, blockchain\, Generative AI\, larg e language models (LLMs)\, software security\, and AI applications in cybe rsecurity. He has authored over 200 peer-reviewed publications with more t han 16\,700 citations and an h-index of 61. He has led international colla borative research projects with institutions in the UK\, Australia\, USA\, Canada\, and China\, and has created four widely used cybersecurity datas ets — Edge-IIoT\, FormAI\, CyberMetric\, and DIA — now extensively ado pted by the AI research community.\n\nHis work has received multiple prest igious awards\, including the 2021 IEEE TEM Best Paper Award\, the 2022 Sc opus Algeria Award\, the 2024 ICT Express Best Paper Award\, and the 2024 IEEE ComSoc CSIM TC Best Journal Paper Award. He has been listed among Sta nford University’s Top 2% Scientists six consecutive times (2020–2025) and was named in the 2025 Clarivate Highly Cited Researchers list. He cur rently serves as Associate Editor for the IEEE Internet of Things Journal and ICT Express (Elsevier) and is a Senior Member of IEEE.\n\nBrochure (PD F): [Webinar-AIML-2026-04-16-Ferrag-6GBench-Brochure.pdf](https://drive.go ogle.com/file/d/190jBcLtqAj4zH02fSihwyZhuruU0fuu4/view)\n\nCo-sponsored by : Future Networks Artificial Intelligence & Machine Learning (AIML) Workin g Group\n\nVirtual: https://events.vtools.ieee.org/m/544689 LOCATION:Virtual: https://events.vtools.ieee.org/m/544689 ORGANIZER:baw@ieee.org SEQUENCE:25 SUMMARY:6G-Bench: Evaluating Semantic Communication and Network-Level Reaso ning in AI-Native 6G Systems URL;VALUE=URI:https://events.vtools.ieee.org/m/544689 X-ALT-DESC:Description: <br /><p class="MsoNormal" style="margin-top: .25in \;"><img src="https://events.vtools.ieee.org/vtools_ui/media/display/93e33 d7d-5c31-4227-8c00-deda82e3e4e3" alt="6G-Bench: : Evaluating Semantic Comm unication and Network-Level Reasoning in AI-Native 6G Systems" width="750" height="197"></p>\n<p class="MsoNormal" style="margin-top: 12.0pt\;">Spec ial Presentation by<strong> Mohamed Amine Ferrag (UAE University\, UAE)</s trong></p>\n<p class="MsoNormal" style="margin-top: 12.0pt\;">Hosted by th e Future Networks<strong> Artificial Intelligence &amp\; Machine Learning (AIML) Working Group</strong></p>\n<p class="MsoNormal" style="margin-top: 12.0pt\;"><strong><span style="font-size: 14.0pt\; font-family: Copperpla te\; mso-fareast-font-family: PMingLiU\; mso-fareast-theme-font: minor-far east\; mso-bidi-font-family: Arial\; mso-bidi-theme-font: minor-bidi\; mso -ansi-language: EN-US\; mso-fareast-language: ZH-TW\; mso-bidi-language: A R-SA\;">Date/Time</span></strong><span style="font-size: 12.0pt\; font-fam ily: 'Calibri'\,sans-serif\; mso-ascii-theme-font: minor-latin\; mso-farea st-font-family: PMingLiU\; mso-fareast-theme-font: minor-fareast\; mso-han si-theme-font: minor-latin\; mso-bidi-font-family: Arial\; mso-bidi-theme- font: minor-bidi\; mso-ansi-language: EN-US\; mso-fareast-language: ZH-TW\ ; mso-bidi-language: AR-SA\;">: <strong>Thursday\, 16 April 2026</strong>< strong>&nbsp\;@ 12:00 UTC (12 PM GMT)</strong></span></p>\n<p class="MsoNo rmal" style="margin-top: .25in\;"><strong><u><span style="font-size: 16.0p t\; font-family: Copperplate\;">Topic</span></u></strong><strong><span sty le="font-size: 16.0pt\; font-family: Copperplate\;">:</span></strong></p>\ n<p class="MsoNormal"><strong><span style="font-size: 16pt\;">6G-Bench: Ev aluating Semantic Communication and Network-Level Reasoning in AI-Native 6 G Systems&nbsp\;</span></strong></p>\n<p class="MsoNormal" style="margin-t op: .25in\;"><strong><u><span style="font-size: 16.0pt\; font-family: Copp erplate\;">Abstract</span></u></strong><strong><span style="font-size: 16. 0pt\; font-family: Copperplate\;">:</span></strong></p>\n<p>Emerging sixth -generation (6G) networks are envisioned as AI-native systems in which fou ndation models act as high-level reasoning and coordination layers above s tandardized network functions. While large language models (LLMs) have dem onstrated strong capabilities in isolated wireless and networking tasks\, their ability to perform network-level semantic reasoning over intents\, p olicies\, trust constraints\, and multi-agent coordination remains insuffi ciently evaluated.</p>\n<p>In this talk\, I will present 6G-Bench\, an ope n benchmark designed to rigorously assess semantic communication and netwo rk-level reasoning in AI-native 6G environments. The benchmark defines a t axonomy of 30 decision-making tasks aligned with ongoing standardization e fforts in 3GPP\, IETF\, ETSI\, ITU-T\, and the O-RAN Alliance. These tasks are grouped into five capability categories: intent and policy reasoning\ , network slicing and resource management\, trust and security awareness\, AI-native networking and agentic control\, and distributed intelligence f or emerging 6G use cases.</p>\n<p>Starting from over 113\,000 realistic 6G operational scenarios\, we construct 10\,000 very-hard\, task-conditioned multiple-choice questions that require multi-step quantitative reasoning under uncertainty and worst-case regret minimization. After automated filt ering and expert validation\, 3\,722 high-confidence questions form the fi nal evaluation set.</p>\n<p>I will also present a comprehensive evaluation of 22 contemporary foundation models and discuss key insights for deployi ng AI reasoning layers in future AI-native 6G networks.</p>\n<p><strong><s pan style="font-size: 16.0pt\; font-family: Copperplate\;"><u>Speaker</u>: </span></strong></p>\n<table style="border-collapse: collapse\; width: 100 %\;" border="1"><colgroup><col style="width: 14.779271%\;"><col style="wid th: 85.12476%\;"></colgroup>\n<tbody>\n<tr>\n<td><img src="https://events. vtools.ieee.org/vtools_ui/media/display/4fb0bcf6-f4f3-49b9-8ff1-62d7019ffd b6" alt="" width="127" height="150"></td>\n<td>\n<p class="MsoNormal" styl e="margin-top: 6.0pt\;"><strong>Mohamed Amine Ferrag</strong> earned his B achelor&rsquo\;s\, Master&rsquo\;s\, Ph.D.\, and Habilitation degrees in C omputer Science from Badji Mokhtar&mdash\;Annaba University\, Algeria\, in 2008\, 2010\, 2014\, and 2019\, respectively. He served as an Associate P rofessor at Guelma University\, Algeria (2014&ndash\;2022)\, and as a Seni or Researcher at the NAU-Lincoln Joint Research Center for Intelligent Eng ineering\, Nanjing Agricultural University\, China (2019&ndash\;2022). Fro m 2022 to 2024\, he was Lead Researcher at the Technology Innovation Insti tute (TII)\, Abu Dhabi\, where he led AI-driven cybersecurity research ini tiatives. In 2025\, he joined the United Arab Emirates University (UAEU) a s an Associate Professor in the Department of Computer and Network Enginee ring.</p>\n<p class="MsoNormal" style="margin-top: 6.0pt\;">His research f ocuses on cybersecurity and AI-native systems\, including wireless network security\, network coding security\, applied cryptography\, blockchain\, Generative AI\, large language models (LLMs)\, software security\, and AI applications in cybersecurity. He has authored over 200 peer-reviewed publ ications with more than 16\,700 citations and an h-index of 61. He has led international collaborative research projects with institutions in the UK \, Australia\, USA\, Canada\, and China\, and has created four widely used cybersecurity datasets &mdash\; Edge-IIoT\, FormAI\, CyberMetric\, and DI A &mdash\; now extensively adopted by the AI research community.</p>\n<p c lass="MsoNormal" style="margin-top: 6.0pt\;">His work has received multipl e prestigious awards\, including the 2021 IEEE TEM Best Paper Award\, the 2022 Scopus Algeria Award\, the 2024 ICT Express Best Paper Award\, and th e 2024 IEEE ComSoc CSIM TC Best Journal Paper Award. He has been listed am ong Stanford University&rsquo\;s Top 2% Scientists six consecutive times ( 2020&ndash\;2025) and was named in the 2025 Clarivate Highly Cited Researc hers list. He currently serves as Associate Editor for the IEEE Internet o f Things Journal and ICT Express (Elsevier) and is a Senior Member of IEEE .</p>\n</td>\n</tr>\n</tbody>\n</table>\n<p><strong>Brochure (PDF)</strong >: <a href="https://drive.google.com/file/d/190jBcLtqAj4zH02fSihwyZhuruU0f uu4/view" target="_blank" rel="noopener">Webinar-AIML-2026-04-16-Ferrag-6G Bench-Brochure.pdf</a></p> END:VEVENT END:VCALENDAR