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)

Measuring Web Search Behavior

Measuring Web Search Behavior

On the show, Aleksandra Urman and Mykola Makhortykh join us to discuss their work on the comparative analysis of web search behavior using web tracking data. They shared interesting results from their...

21 Nov 202236min

StrategyQA and Big Bench

StrategyQA and Big Bench

Did Aristotle Use a Laptop?  That's a question from the StrategyQA benchmark which highlights the stretch goals for current artificial intelligence systems.  Answering a question like that requires se...

18 Nov 202241min

Ad Blockers Effect on News Consumption

Ad Blockers Effect on News Consumption

While at first glance, the use of ad blockers drops the revenue of news publishers, this may not be completely true. On the show today, Shunyao Yan, an Assistant Professor in Marketing at Leavey Schoo...

14 Nov 202238min

Your Consent is Worth 75 Euros a Year

Your Consent is Worth 75 Euros a Year

People who do not want their data tracked and shared online can pay a token for a cookie paywall. But are the websites keeping to their side of the bargain? Victor Morel, a Postdoc candidate at the Ch...

7 Nov 202224min

Automated Email Generation for Targeted Attacks

Automated Email Generation for Targeted Attacks

The advancement of generative language models has been a force for good, but also for evil. On the show, Avisha Das, a post-doctoral scholar at the University of Texas Health Center, joins us to discu...

31 Okt 202245min

Tribal Marketing

Tribal Marketing

Peter Gloor, a Research Scientist at the MIT Center for Collective Intelligence, takes us on a new world of tribe classification. He extensively discussed the need for such classification on the inter...

24 Okt 202237min

Nano-targetted Facebook Ads

Nano-targetted Facebook Ads

17 Okt 202244min

Debiasing GPT-3 Job Ads

Debiasing GPT-3 Job Ads

We hear about the impeccable achievements of GPT-3 models, but such large generative models come with their bias. On the show today, Conrad Borchers, a Ph.D. student in Human-Computer Interaction, joi...

10 Okt 202248min

Populært innen Vitenskap

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