BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Data-Agnostic Model Poisoning to Manipulating Federated Learning -
  Kai (Lukas) Li\, CISTER research centre\, Portugal
DTSTART:20240716T130000Z
DTEND:20240716T140000Z
UID:TALK216895@talks.cam.ac.uk
CONTACT:Anna Talas
DESCRIPTION:In this presentation\, a data-agnostic model poisoning attack 
 targeting federated learning systems will be explored. The proposed attack
  leverages a new adversarial graph autoencoder (GAE)-based framework that 
 operates independently of training data access\, thereby ensuring both its
  efficacy and stealth. The proposed attack allows the adversary to reconst
 ruct the graph's structural correlations adversarially\, optimizing the di
 sruption of federated learning performance. This is achieved by generating
  malicious local models that incorporate the adversarial graph structure a
 longside the benign features of training data. Furthermore\, an algorithm 
 has been developed to iteratively refine the malicious models using GAE wi
 th sub-gradient descent. Numerical results demonstrate a progressive decli
 ne in the accuracy of federated learning systems subjected to this attack\
 , which notably eludes detection by existing defensive measures. Consequen
 tly\, this attack presents a formidable risk\, potentially compromising al
 l benign devices within the network.\n\nShort bio: Dr. Kai Li received the
  B.E. degree from Shandong University\, China\, in 2009\, the M.S. degree 
 from The Hong Kong University of Science and Technology\, Hong Kong\, in 2
 010\, and the Ph.D. degree in computer science from The University of New 
 South Wales\, Sydney\, NSW\, Australia\, in 2014. Currently\, he is a Visi
 ting Research Scientist with the Division of Electrical Engineering\, Depa
 rtment of Engineering\, University of Cambridge\, U.K.\, and a Senior Rese
 arch Scientist with the CISTER Research Centre\, Porto\, Portugal. He is a
 lso a CMU-Portugal Research Fellow\, jointly supported by Carnegie Mellon 
 University (CMU)\, Pittsburgh\, PA\, USA\, and the Foundation for Science 
 and Technology (FCT)\, Lisbon\, Portugal. In 2022\, he was a Visiting Rese
 arch Scholar with the CyLab Security and Privacy Institute\, CMU. Prior to
  this\, he was a Post-Doctoral Research Fellow with the SUTD-MIT Internati
 onal Design Centre\, Singapore University of Technology and Design\, Singa
 pore\, from 2014 to 2016. He has also held positions as a Visiting Researc
 h Assistant with the ICT Centre\, CSIRO\, Brisbane\, QLD\, Australia\, fro
 m 2012 to 2013\, and a full-time Research Assistant with the Mobile Techno
 logies Centre\, The Chinese University of Hong Kong\, Hong Kong\, from 201
 0 to 2011. He has been an Associate Editor of journals\, such as Internet 
 of Things (Elsevier) since 2024\, Nature Computer Science (Springer) since
  2023\, Computer Communications (Elsevier) and Ad Hoc Networks (Elsevier) 
 since 2021\, and IEEE ACCESS from 2018 to 2024.\n\nhttps://us02web.zoom.us
 /j/84571416210?pwd=LyRMbZjKUaUtGzSJQam8A5NRcGgoah.1\n\nMeeting ID: 845 714
 1 6210\nPasscode: 916045\n\nRECORDING : Please note\, this event will be r
 ecorded and will be available after the event for an indeterminate period 
 under a CC BY -NC-ND license. Audience members should bear this in mind be
 fore joining the webinar or asking questions.\n\nNOTE : Please do not post
  URLs for the talk\, and especially Zoom links to Twitter because automate
 d systems will pick them up and disrupt our meeting.
LOCATION:Webinar &amp\; LT2\, Computer Laboratory\, William Gates Building
 .
END:VEVENT
END:VCALENDAR