Easily Fooling Deep Neural Networks
Data Skeptic16 Jan 2015

Easily Fooling Deep Neural Networks

My guest this week is Anh Nguyen, a PhD student at the University of Wyoming working in the Evolving AI lab. The episode discusses the paper Deep Neural Networks are Easily Fooled [pdf] by Anh Nguyen, Jason Yosinski, and Jeff Clune. It describes a process for creating images that a trained deep neural network will mis-classify. If you have a deep neural network that has been trained to recognize certain types of objects in images, these "fooling" images can be constructed in a way which the network will mis-classify them. To a human observer, these fooling images often have no resemblance whatsoever to the assigned label. Previous work had shown that some images which appear to be unrecognizable white noise images to us can fool a deep neural network. This paper extends the result showing abstract images of shapes and colors, many of which have form (just not the one the network thinks) can also trick the network.

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(601)

Earthquake Detection with Crowd-sourced Data

Earthquake Detection with Crowd-sourced Data

Have you ever wanted to hear what an earthquake sounds like? Today on the show we have Omkar Ranadive, Computer Science Masters student at NorthWestern University, who collaborates with Suzan van der ...

25 Des 202029min

Byzantine Fault Tolerant Consensus

Byzantine Fault Tolerant Consensus

Byzantine fault tolerance (BFT) is a desirable property in a distributed computing environment. BFT means the system can survive the loss of nodes and nodes becoming unreliable. There are many differe...

22 Des 202035min

Alpha Fold

Alpha Fold

Kyle shared some initial reactions to the announcement about Alpha Fold 2's celebrated performance in the CASP14 prediction.  By many accounts, this exciting result means protein folding is now a solv...

11 Des 202023min

Arrow's Impossibility Theorem

Arrow's Impossibility Theorem

Above all, everyone wants voting to be fair. What does fair mean and how can we measure it? Kenneth Arrow posited a simple set of conditions that one would certainly desire in a voting system. For exa...

4 Des 202026min

Face Mask Sentiment Analysis

Face Mask Sentiment Analysis

As the COVID-19 pandemic continues, the public (or at least those with Twitter accounts) are sharing their personal opinions about mask-wearing via Twitter. What does this data tell us about public op...

27 Nov 202041min

Counting Briberies in Elections

Counting Briberies in Elections

Niclas Boehmer, second year PhD student at Berlin Institute of Technology, comes on today to discuss the computational complexity of bribery in elections through the paper "On the Robustness of Winner...

20 Nov 202037min

Sybil Attacks on Federated Learning

Sybil Attacks on Federated Learning

Clement Fung, a Societal Computing PhD student at Carnegie Mellon University, discusses his research in security of machine learning systems and a defense against targeted sybil-based poisoning called...

13 Nov 202031min

Differential Privacy at the US Census

Differential Privacy at the US Census

Simson Garfinkel, Senior Computer Scientist for Confidentiality and Data Access at the US Census Bureau, discusses his work modernizing the Census Bureau disclosure avoidance system from private to pu...

6 Nov 202029min

Populært innen Vitenskap

fastlegen
tingenes-tilstand
jss
forskningno
rekommandert
rss-zahid-ali-hjelper-deg
rss-paradigmepodden
sinnsyn
vett-og-vitenskap-med-gaute-einevoll
rss-overskuddsliv
nordnorsk-historie
kvinnehelsepodden
tidlose-historier
villmarksliv
liberal-halvtime
rss-inn-til-kjernen-med-sunniva-rose
fjellsportpodden
grunnstoffene
nevropodden
rss-rekommandert