BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.0.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:345@isdm.umontpellier.fr
DTSTART;TZID=Europe/Paris:20231212T140000
DTEND;TZID=Europe/Paris:20231212T140000
DTSTAMP:20260828T084917Z
URL:https://isdm.umontpellier.fr/events/machine-learning-in-untrusted-envi
 ronment/
SUMMARY:Machine Learning in Untrusted Environment
DESCRIPTION:Room 02.124\, Building 5\, St Priest campus\n\nMachine Learning
  in Montpellier\, Theory &amp\; Practice\n\nRecent AI systems make use of 
 machine-learning algorithms\, where the computing system learns from data 
 (observations) in order to adjust its behavior. In fact\, the availability
  of huge amounts of data has been the key enabler of modern AI-based techn
 ologies. This dependency on data\, however\, is also the Achille&#x27\;s h
 eel of AI systems. The data\, which can come from a wide variety of source
 s\, is not always trustworthy. Some sources can provide erroneous or corru
 pted data. With current machine-learning algorithms\, a single &quot\;bad&
 quot\;&quot\; source can lead the entire learning scheme to make critical 
 mistakes. Moreover\, to handle the huge amounts of data\, machine-learning
  algorithms are often deployed over a large number of computing machines. 
 Consequently\, as this number increases\, the likelihood of machine errors
  also increases. Indeed\, software and hardware bugs are prevalent. Furthe
 rmore\, machines can sometimes be hacked by malicious players\, either dir
 ectly or indirectly through viruses. Some of these players attempt to corr
 upt the entire learning procedure\, merely for the pleasure of claiming to
  have destroyed an important system. Others attempt to influence the learn
 ing procedure for their own benefit. Building machine-learning schemes tha
 t are robust to these events is paramount to transitioning AI from being a
  mere spectacle capable of momentary feats to a dependable tool with guara
 nteed safety. In this talk\, we cover some effective techniques for achiev
 ing such robustness. We present machine-learning algorithms that do not tr
 ust any individual data source or computing unit. We do assume\, however\,
  that a majority of data sources and machines are trustworthy\; otherwise\
 , no meaningful learning guarantee can be provided. The challenge arises f
 rom the fact that the identity of the trusted data sources and machines is
  a priori unknown.&quot\;\n\nMachine Learning in Montpellier\, Theory &amp
 \; Practice
ATTACH;FMTTYPE=image/jpeg:https://isdm.umontpellier.fr/wp-content/uploads/
 2026/06/ml-mtp-gC78d5.png
CATEGORIES:ML MTP
LOCATION:Saint Priest Campus - Building 5 - Room 02.124\, 860 rue St Priest
 \, Montpellier\, 
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=860 rue St Priest\, Montpel
 lier\, ;X-APPLE-RADIUS=100;X-TITLE=Saint Priest Campus - Building 5 - Room
  02.124:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20231029T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR