Player is loading...

Embed

Copy embed code

Transcriptions

Note: this content has been automatically generated.
00:00:02
a professor should grow we a slab and with my quarters work on to accept
00:00:07
um so today if it kind of safe if you go to
00:00:10
an airport and pass although security checks done by humans
00:00:15
should you feel safe windows security chit checks we did on
00:00:18
the machine learning algorithms artificial intelligence well yes and no
00:00:22
i know if i tell you that today uh terrorists country d. printable changed
00:00:27
if you pick sets a few meters in the colour of the bob
00:00:30
and make a classifier in the airport say this is a cute find this actually happened with a classifier
00:00:36
and yes a a a because more and more people and researchers are working on
00:00:40
the field i sit in in particular here at e. p. f. l.
00:00:43
we've uh come up with a couple of solutions to the vulnerabilities of machinery machine
00:00:47
and it has a lot of unabridged i'll talk about one in particular average
00:00:52
machine learning relies heavily on average and if you have done some basics astrology you'd know that
00:00:59
averaging is the worst way to compare two populations for example if you take the g. d. p. of denmark
00:01:04
averaged over the population of that market gets a lower value if you do the same averaging over the
00:01:09
us population and no one is full to the to say that the typical us citizen is richer
00:01:14
or comparable to the done and then use it is the same for this room is the is the billionaire in the room
00:01:19
the average income of this room is a hundred million that's this is a very bad way to classify rules were academics
00:01:27
so uh of course machinery resources no an alternative to average of the media
00:01:32
the meeting is very easy in single dimension of uh of variables you just take the
00:01:36
bible's rank them and take the one that separates the population into two parts
00:01:40
and this would be robust classifier that's determined that machine learning gives in very
00:01:44
high dimensional space is a models are vectors of a hundred billion parameters
00:01:50
and you can just rank them and take the how the this value that separates the need to to hop operations
00:01:55
so we michael cocoa cultures would come up with a with alternatives
00:01:59
that are practical and that we proved mathematically are safe
00:02:03
uh both alternatives i'm somehow inspired by the median but others
00:02:07
are lip shoots filters or uh other utterances we've
00:02:11
presented our results uh to the machine and you'd you so uh they are kind of
00:02:15
accepted and now uh we are implementing that as a system on top of concerts
00:02:20
i would also tackled some other topics in i. c. t. like safe interrupt ability and three
00:02:24
years this can happen inside a neural network at an individual neural more on uh
00:02:30
a level and if you're interested in details and the details of this works so

Share this talk: 


Conference Program

Welcome address
Andreas Mortensen, Vice President for Research, EPFL
June 7, 2018 · 9:49 a.m.
799 views
Introduction
Jim Larus, Dean of IC School, EPFL
June 7, 2018 · 10 a.m.
254 views
The Young Software Engineer’s Guide to Using Formal Methods
K. Rustan M. Leino, Amazon
June 7, 2018 · 10:16 a.m.
959 views
Safely Disrupting Computer Networks with Software
Katerina Argyraki, EPFL
June 7, 2018 · 11:25 a.m.
1433 views
Short IC Research Presentation 2: Gamified Rehabilitation with Tangible Robots
Arzu Guneysu Ozgur, EPFL (CHILI)
June 7, 2018 · 12:15 p.m.
353 views
Short IC Research Presentation 3: kickoff.ai
Lucas Maystre, Victor Kristof, EPFL (LCA)
June 7, 2018 · 12:19 p.m.
164 views
Short IC Research Presentation 4: Neural Network Guided Expression Transformation
Romain Edelmann, EPFL (LARA)
June 7, 2018 · 12:22 p.m.
160 views
Short IC Research Presentation 5: CleanM
Stella Giannakopoulo, EPFL (DIAS)
June 7, 2018 · 12:25 p.m.
164 views
Short IC Research Presentation 6: Understanding Cities through Data
Eleni Tzirita Zacharatou, EPFL (DIAS)
June 7, 2018 · 12:27 p.m.
1916 views
Short IC Research Presentation 7: Datagrowth and application trends
Matthias Olma, EPFL (DIAS)
June 7, 2018 · 12:31 p.m.
102 views
Short IC Research Presentation 8: Point Cloud, a new source of knowledge
Mirjana Pavlovic, EPFL (DIAS)
June 7, 2018 · 12:34 p.m.
169 views
Short IC Research Presentation 9: To Click or not to Click?
Eleni Tzirita Zacharatou, EPFL (DIAS)
June 7, 2018 · 12:37 p.m.
233 views
Short IC Research Presentation 10: RaaSS Reliability as a Software Service
Maaz Mohiuddlin, LCA2, IC-EPFL
June 7, 2018 · 12:40 p.m.
134 views
Short IC Research Presentation 11: Adversarial Machine Learning in Byzantium
El Mahdi El Mhamdi, EPFL (LPD)
June 7, 2018 · 12:43 p.m.
438 views
20s pitch 1: Cost and Energy Efficient Data Management
Utku Sirin, (DIAS)
June 7, 2018 · 2:20 p.m.
196 views
20s pitch 5: Unified, High Performance Data Cleaning
Stella Giannakopoulo, EPFL (DIAS)
June 7, 2018 · 2:21 p.m.
20s pitch 4: Neural Network Guided Expression Transformation
Romain Edelmann, EPFL (LARA)
June 7, 2018 · 2:21 p.m.
20s pitch 2: Gamification of Rehabilitation
Arzu Guneysu Ozgur, EPFL (CHILI)
June 7, 2018 · 2:21 p.m.
106 views
20s pitch 6: Interactive Exploration of Urban Data with GPUs
Eleni Tzirita Zacharatou, EPFL (DIAS)
June 7, 2018 · 2:22 p.m.
181 views
20s pitch 7: Interactive Data Exploration
Matthias Olma, EPFL (DIAS)
June 7, 2018 · 2:22 p.m.
20s pitch 8: Efficient Point Cloud Processing
Mirjana Pavlovic, EPFL (DIAS)
June 7, 2018 · 2:23 p.m.
234 views
20s pitch 9: To Click or not to Click?
Eleni Tzirita Zacharatou, EPFL (DIAS)
June 7, 2018 · 2:24 p.m.
232 views
20s pitch 10: RaaSS Reliability as a Software Service
Maaz Mohiuddlin, LCA2, IC-EPFL
June 7, 2018 · 2:24 p.m.
118 views
20s pitch 11: Adversarial Machine Learning in Byzantium
El Mahdi El Mhamdi, EPFL (LPD)
June 7, 2018 · 2:24 p.m.
170 views
Machine Learning: Alchemy for the Modern Computer Scientist
Erik Meijer, Facebook
June 7, 2018 · 2:29 p.m.
797 views