Data Skeptic21 Sep 2018

Deep Fakes

Digital videos can be described as sequences of still images and associated audio. Audio is easy to fake. What about video?

A video can easily be broken down into a sequence of still images replayed rapidly in sequence. In this context, videos are simply very high dimensional sequences of observations, ripe for input into a machine learning algorithm.

The availability of commodity hardware, clever algorithms, and well-designed software to implement those algorithms at scale make it possible to do machine learning on video, but to what end? There are many answers, one interesting approach being the technology called "DeepFakes".

The Deep of Deepfakes refers to Deep Learning, and the fake refers to the function of the software - to take a real video of a human being and digitally alter their face to match someone else's face. Here are two examples:

This software produces curiously convincing fake videos. Yet, there's something slightly off about them. Surely machine learning can be used to determine real from fake... right? Siwei Lyu and his collaborators certainly thought so and demonstrated this idea by identifying a novel, detectable feature which was commonly missing from videos produced by the Deep Fakes software.

In this episode, we discuss this use case for deep learning, detecting fake videos, and the threat of fake videos in the future.

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

Episoder(601)

Data Science at ZestFinance with Marick Sinay

Marick Sinay from ZestFianance is our guest this weel. This episode explores how data science techniques are applied in the financial world, specifically in assessing credit worthiness.

12 Sep 201431min

[MINI] Decision Tree Learning

Linhda and Kyle talk about Decision Tree Learning in this miniepisode. Decision Tree Learning is the algorithmic process of trying to generate an optimal decision tree to properly classify or forecas...

5 Sep 201413min

Jackson Pollock Authentication Analysis with Kate Jones-Smith

Our guest this week is Hamilton physics professor Kate Jones-Smith who joins us to discuss the evidence for the claim that drip paintings of Jackson Pollock contain fractal patterns. This hypothesis o...

29 Aug 201449min

[MINI] Noise!!

Our topic for this week is "noise" as in signal vs. noise. This is not a signal processing discussions, but rather a brief introduction to how the work noise is used to describe how much information ...

22 Aug 201416min

Guerilla Skepticism on Wikipedia with Susan Gerbic

Our guest this week is Susan Gerbic. Susan is a skeptical activist involved in many activities, the one we focus on most in this episode is Guerrilla Skepticism on Wikipedia, an organization working t...

15 Aug 20141h 9min

[MINI] Ant Colony Optimization

In this week's mini episode, Linhda and Kyle discuss Ant Colony Optimization - a numerical / stochastic optimization technique which models its search after the process ants employ in using random wal...

8 Aug 201415min

Data in Healthcare IT with Shahid Shah

Our guest this week is Shahid Shah. Shahid is CEO at Netspective, and writes three blogs: Health Care Guy, Shahid Shah, and HitSphere - the Healthcare IT Supersite. During the program, Kyle recommend...

1 Aug 201457min

[MINI] Cross Validation

This miniepisode discusses the technique called Cross Validation - a process by which one randomly divides up a dataset into numerous small partitions. Next, (typically) one is held out, and the rest ...

25 Jul 20140s