BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Europe/London BEGIN:DAYLIGHT DTSTART:20260329T020000 TZOFFSETFROM:+0000 TZOFFSETTO:+0100 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:BST END:DAYLIGHT BEGIN:STANDARD DTSTART:20261025T010000 TZOFFSETFROM:+0100 TZOFFSETTO:+0000 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 TZNAME:GMT END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260723T144947Z UID:1F771781-C234-4184-AF4D-66BA348850A2 DTSTART;TZID=Europe/London:20260716T150000 DTEND;TZID=Europe/London:20260716T160000 DESCRIPTION:Title: Poisoning-Resilient Federated Learning for Intrusion Det ection in Industrial IoT\n\nSpeaker: Dr Segun Popoola\n\nAbstract:\nFedera ted learning is increasingly being explored for privacy-preserving intrusi on detection in Industrial Internet of Things (IIoT) environments\, where raw traffic data may be sensitive\, distributed\, or difficult to centrali ze. However\, the same distributed training process creates a poisoning at tack surface in which compromised clients can corrupt local data\, flip la bels\, inject backdoor triggers\, or submit malicious model updates that i nfluence the global intrusion detection model. This presentation will prov ide a focused overview of poisoning-related threats in federated learning- based intrusion detection systems\, including data poisoning\, label-flipp ing attacks\, backdoor poisoning\, malicious updates\, and Byzantine or ou tlying client behaviour. It will also critically review emerging defence s trategies such as robust aggregation\, anomaly filtering\, trust-aware wei ghting\, knowledge distillation\, and backdoor-specific detection. The tal k will conclude by presenting a conceptual framework for poisoning-resilie nt federated intrusion detection that combines client profiling\, poisonin g detection\, robust aggregation\, dynamic trust management\, and recovery -oriented governance throughout the federated learning lifecycle.\n\nBio:\ nDr Segun Popoola is a Senior Lecturer in the School of Computing and Info rmation Science at Anglia Ruskin University\, UK. His research focuses on the intersection of cyber security\, artificial intelligence\, federated l earning\, Internet of Things security\, smart critical infrastructure\, an d wireless communications. He has published extensively in these areas\, i ncluding work on federated deep learning for intrusion detection and zero- day botnet attack detection in IoT-edge environments. He is a Member of IE EE and has contributed to several research and innovation projects involvi ng AI-driven cyber security\, IoT security\, and federated learning. His b roader research interests include the security of AI systems\, intrusion d etection\, deep learning\, smart critical infrastructure\, and privacy-pre serving collaborative intelligence.\n\nVirtual: https://events.vtools.ieee .org/m/566307 LOCATION:Virtual: https://events.vtools.ieee.org/m/566307 ORGANIZER:hujun.yin@manchester.ac.uk SEQUENCE:1 SUMMARY:Seminar: Poisoning-Resilient Federated Learning for Intrusion Detec tion in Industrial IoT URL;VALUE=URI:https://events.vtools.ieee.org/m/566307 X-ALT-DESC:Description: <br /><div class="x_skipProofing">Title:&nbsp\;Pois oning-Resilient Federated Learning for Intrusion Detection in Industrial I oT</div>\n<div class="x_skipProofing" aria-hidden="true">&nbsp\;</div>\n<d iv class="x_skipProofing" aria-hidden="true">Speaker: Dr Segun Popoola</di v>\n<div class="x_skipProofing" aria-hidden="true">&nbsp\;</div>\n<div cla ss="x_skipProofing">Abstract:<br>Federated learning is increasingly being explored for privacy-preserving intrusion detection in Industrial Internet of Things (IIoT) environments\, where raw traffic data may be sensitive\, distributed\, or difficult to centralize. However\, the same distributed training process creates a poisoning attack surface in which compromised c lients can corrupt local data\, flip labels\, inject backdoor triggers\, o r submit malicious model updates that influence the global intrusion detec tion model. This presentation will provide a focused overview of poisoning -related threats in federated learning-based intrusion detection systems\, including data poisoning\, label-flipping attacks\, backdoor poisoning\, malicious updates\, and Byzantine or outlying client behaviour. It will al so critically review emerging defence strategies such as robust aggregatio n\, anomaly filtering\, trust-aware weighting\, knowledge distillation\, a nd backdoor-specific detection. The talk will conclude by presenting a con ceptual framework for poisoning-resilient federated intrusion detection&nb sp\;that combines client profiling\, poisoning detection\, robust aggregat ion\, dynamic trust management\, and recovery-oriented governance througho ut&nbsp\;the federated learning lifecycle.</div>\n<div class="x_skipProofi ng" aria-hidden="true">&nbsp\;</div>\n<div class="x_skipProofing">Bio:<br> Dr Segun Popoola is a Senior Lecturer in the School of Computing and Infor mation Science at Anglia Ruskin University\, UK. His research focuses on t he intersection of cyber security\, artificial intelligence\, federated le arning\, Internet of Things security\, smart critical infrastructure\, and wireless communications. He has published extensively in these areas\, in cluding work on federated deep learning for intrusion detection and zero-d ay botnet attack detection in IoT-edge environments. He is a Member of IEE E and has contributed to several research and innovation projects involvin g AI-driven cyber security\, IoT security\, and federated learning. His br oader research interests include the security of AI systems\, intrusion de tection\, deep learning\, smart critical infrastructure\, and privacy-pres erving collaborative intelligence.</div> END:VEVENT END:VCALENDAR