Embed code
Note: this content has been automatically generated.
a professor should grow we a slab and with my quarters work on to accept
um so today if it kind of safe if you go to
an airport and pass although security checks done by humans
should you feel safe windows security chit checks we did on
the machine learning algorithms artificial intelligence well yes and no
i know if i tell you that today uh terrorists country d. printable changed
if you pick sets a few meters in the colour of the bob
and make a classifier in the airport say this is a cute find this actually happened with a classifier
and yes a a a because more and more people and researchers are working on
the field i sit in in particular here at e. p. f. l.
we've uh come up with a couple of solutions to the vulnerabilities of machinery machine
and it has a lot of unabridged i'll talk about one in particular average
machine learning relies heavily on average and if you have done some basics astrology you'd know that
averaging is the worst way to compare two populations for example if you take the g. d. p. of denmark
averaged over the population of that market gets a lower value if you do the same averaging over the
us population and no one is full to the to say that the typical us citizen is richer
or comparable to the done and then use it is the same for this room is the is the billionaire in the room
the average income of this room is a hundred million that's this is a very bad way to classify rules were academics
so uh of course machinery resources no an alternative to average of the media
the meeting is very easy in single dimension of uh of variables you just take the
bible's rank them and take the one that separates the population into two parts
and this would be robust classifier that's determined that machine learning gives in very
high dimensional space is a models are vectors of a hundred billion parameters
and you can just rank them and take the how the this value that separates the need to to hop operations
so we michael cocoa cultures would come up with a with alternatives
that are practical and that we proved mathematically are safe
uh both alternatives i'm somehow inspired by the median but others
are lip shoots filters or uh other utterances we've
presented our results uh to the machine and you'd you so uh they are kind of
accepted and now uh we are implementing that as a system on top of concerts
i would also tackled some other topics in i. c. t. like safe interrupt ability and three
years this can happen inside a neural network at an individual neural more on uh
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
7 June 2018 · 9:49 a.m.
Introduction
Jim Larus, Dean of IC School, EPFL
7 June 2018 · 10 a.m.
The Young Software Engineer’s Guide to Using Formal Methods
K. Rustan M. Leino, Amazon
7 June 2018 · 10:16 a.m.
Safely Disrupting Computer Networks with Software
Katerina Argyraki, EPFL
7 June 2018 · 11:25 a.m.
Short IC Research Presentation 3: kickoff.ai
Lucas Maystre, Victor Kristof, EPFL (LCA)
7 June 2018 · 12:19 p.m.
Short IC Research Presentation 5: CleanM
Stella Giannakopoulo, EPFL (DIAS)
7 June 2018 · 12:25 p.m.
Short IC Research Presentation 7: Datagrowth and application trends
Matthias Olma, EPFL (DIAS)
7 June 2018 · 12:31 p.m.
Short IC Research Presentation 8: Point Cloud, a new source of knowledge
Mirjana Pavlovic, EPFL (DIAS)
7 June 2018 · 12:34 p.m.
Short IC Research Presentation 9: To Click or not to Click?
Mahsa Taziki, EPFL (LPD)
7 June 2018 · 12:37 p.m.
Short IC Research Presentation 10: RaaSS Reliability as a Software Service
Maaz Mohiuddlin, LCA2, IC-EPFL
7 June 2018 · 12:40 p.m.
20s pitch 2: Gamification of Rehabilitation
Arzu Guneysu Ozgur, EPFL (CHILI)
7 June 2018 · 2:21 p.m.
20s pitch 4: Neural Network Guided Expression Transformation
Romain Edelmann, EPFL (LARA)
7 June 2018 · 2:21 p.m.
20s pitch 5: Unified, High Performance Data Cleaning
Stella Giannakopoulo, EPFL (DIAS)
7 June 2018 · 2:21 p.m.
20s pitch 6: Interactive Exploration of Urban Data with GPUs
Eleni Tzirita Zacharatou, EPFL (DIAS)
7 June 2018 · 2:22 p.m.
20s pitch 7: Interactive Data Exploration
Matthias Olma, EPFL (DIAS)
7 June 2018 · 2:22 p.m.
20s pitch 8: Efficient Point Cloud Processing
Mirjana Pavlovic, EPFL (DIAS)
7 June 2018 · 2:23 p.m.
20s pitch 9: To Click or not to Click?
Mahsa Taziki, EPFL (LPD)
7 June 2018 · 2:24 p.m.
20s pitch 10: RaaSS Reliability as a Software Service
Maaz Mohiuddlin, LCA2, IC-EPFL
7 June 2018 · 2:24 p.m.
20s pitch 11: Adversarial Machine Learning in Byzantium
El Mahdi El Mhamdi, EPFL (LPD)
7 June 2018 · 2:24 p.m.

Recommended talks

Advanced Functional Fibers
Fabien Sorin, Laboratory of Photonic Materials and Fibre Devices
16 March 2017 · 11:51 a.m.