BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//chikkutakku.com//RDFCal 1.0//EN
X-WR-CALDESC:GoogleカレンダーやiCalendar形式情報を共有シェ
 アしましょう。近所のイベントから全国のイベントま
 で今日のイベント検索やスケジュールを決めるならち
 っくたっく
X-WR-CALNAME:ちっくたっく
X-WR-TIMEZONE:UTC
BEGIN:VEVENT
SUMMARY:School of IT seminar slot (compulsory if scheduled)
DTSTART;VALUE=DATE-TIME:20260423T110000Z
DTEND;VALUE=DATE-TIME:20260423T115000Z
UID:169530431401
DESCRIPTION:Speaker: Sabre Didi Title: Co-evolutionary Adversarial Lear
 ning for Robust Malware DetectionAbstract: Adversarial attacks pose a gro
 wing challenge to machine learning systems used in malware detection\, par
 ticularly when models rely on complex\, high-dimensional feature represent
 ations such as those found in the EMBER dataset. In this talk\, I present 
 a co-evolutionary adversarial training framework designed to improve the r
 obustness of such systems. The approach combines gradient-based adversaria
 l attacks with evolutionary optimisation to create adaptive and increasing
 ly challenging adversaries. A hybrid CNN–MLP model is used to capture bo
 th structural patterns and metadata features within malware samples. Adver
 sarial examples are generated using Projected Gradient Descent (PGD)\; how
 ever\, rather than relying on fixed parameters\, an evolutionary controlle
 r dynamically adjusts the attack strategy based on gradient information. T
 his results in an online co-evolutionary process in which the classifier a
 nd adversary continuously adapt to one another\, mirroring the real-world 
 arms race in malware detection. Experimental results show that this method
  improves robustness against adversarial attacks while maintaining strong 
 performance on clean data. This work highlights how combining deep learnin
 g with evolutionary strategies can lead to more resilient cybersecurity sy
 stems and provides insight into the future of adaptive defence mechanisms 
 in adversarial environments.Biography:Dr. Sabre Z. Didi completed his PhD 
 (2018) in Computer Science and undertook postdoctoral research (2019–202
 2) in the evolutionary machine learning research group under the supervisi
 on of Professor Geoff Nitschke at the University of Cape Town (UCT)\, spec
 ialising in Evolutionary (Robotic) Controller Design. Between 2018 and 202
 5\, he worked in the software development industry across multiple organis
 ations\, holding roles of increasing responsibility\, including positions 
 in AI engineering and software development. Notably\, he worked as an AI a
 nd Software Engineer at Sedna\, a UK-based company specialising in the mar
 itime sector. He is currently a Lecturer at the Cape Peninsula University 
 of Technology in the Department of Information Technology.
LOCATION:John Day LT1
END:VEVENT
END:VCALENDAR