Understanding encryption protected path

[jondeker]

In this article covering hdcp:
http://www.anandtech.com/show/2622/2

The problem is that the movie studios wanted a way of securing the content between the time the AACS was decrypted and the HDCP encryption took over. Once the AACS was decrypted the encoded movie was sitting in main memory and could be intercepted by any other application, so something had to be done.

The solution was to re-encrypt the data once it was pulled off the disc (I'm not kidding). This time the encryption would be done by the application and decrypted by the GPU itself, creating a protected path that couldn't easily be compromised.

If the application is decrypting its input and then re-encrypting for output, doesn't the information sit un-encrypted at some point within the application? Couldn't a hacker somehow monitor/eavesdrop/hack the application to pull out the un-encrypted video?

Could someone explain this? I'm just interested in the theory, not any tools or guides.

 

[DominionSeraph]

Couldn't a hacker somehow monitor/eavesdrop/hack the application to pull out the un-encrypted video?

The likely difference is that if the application is designed to crap out unencrypted data, you are no longer "compromising encryption" as per the DMCA when you access it.
To break the application so that it dumps unencrypted data is to compromise the encryption.