Reverse Engineering “The Seven Words (and More) You Can’t Say On TV”

For as visionary as he was, [George Carlin] vastly underestimated the situation with his classic “Seven Words You Can’t Say on TV” bit. At least judging by [Ben Eater]’s reverse engineering of the “TVGuardian Foul Language Filter” device, it seems like the actual number is at least 20 times that.

To begin at the beginning, a couple of weeks ago [Alec] over at everyone’s favorite nerd hangout Technology Connections did a video on the TVGuardian, a device that attempted to clean up the language of live TV and recorded programming. Go watch that video for the details, but for a brief summary, TVGuardian worked by scanning the closed caption text for naughty words and phrases, muted the audio when something suggestive was found in a lookup table, and inserted a closed caption substitute for the offensive content. In his video, [Alec] pined for a way to look at the list of verboten words, and [Ben] accepted the challenge.

The naughty word list ended up living on a 93LC86 serial EEPROM, which [Ben] removed from his TVGuardian for further exploration. Rather than just plug it into a programmer and dumping the contents, he decided to roll his own decoder with an Arduino, because that’s more fun. And can we just point out our ongoing amazement that [Ben] is able to make watching someone else code interesting?

The resulting NSFW word list is titillating, of course, and the video would be plenty satisfying if that’s where it ended. But [Ben] went further and figured out how the list is organized, how the dirty-to-clean substitutions are made, and even how certain words are whitelisted. That last bit resulted in the revelation that Hollywood legend [Dick Van Dyke] gets a special whitelisting, lest his name becomes sanitized to a hilarious [Jerk Van Gay].

Hats off to [Alec] for inspiring [Ben]’s fascinating reverse engineering effort here.

Continue reading “Reverse Engineering “The Seven Words (and More) You Can’t Say On TV””

Solar Pi Cluster Scours Internet For Nudes

There seems to be a universal truth on the Internet: if you open up a service to the world, eventually somebody will come in and try to mess it up. If you have a comment section, trolls will come in and fill it with pedantic complaints (so we’ve heard anyway, naturally we have no experience with such matters). If you have a service where people can upload files, then it’s a guarantee that something unsavory is eventually going to take up residence on your server.

Unfortunately, that’s exactly what [Christian Haschek] found while developing his open source image hosting platform, PictShare. He was alerted to some unsavory pictures on PictShare, and after he dealt with them he realized these could be the proverbial tip of the iceberg. But there were far too many pictures on the system to check manually. He decided to build a system that could search for NSFW images using a trained neural network.

The nude-sniffing cluster is made up of a trio of Raspberry Pi computers, each with its own Movidius neural compute stick to perform the heavy lifting. [Christian] explains how he installed the compute stick SDK and Yahoo’s open source learning module for identifying questionable images, the aptly named open_nsfw. The system can be scaled up by adding more Pis to the system, and since it’s all ARM processors and compute sticks, it’s energy efficient enough the whole system can run off a 10 watt solar panel.

After opening up the system with a public web interface where users can scan their own images, he offered his system’s services to a large image hosting provider to see what it would find. Shockingly, the system was able to find over 3,000 images that contained suspected child pornography. The appropriate authorities were notified, and [Christian] encourages anyone else looking to search their servers for this kind of content to drop him a line. Truly hacking for good.

This isn’t the first time we’ve seen Intel’s Movidius compute stick in the wild., and of course we’ve seen our fair share of Raspberry Pi clusters. From 750 node monsters down to builds which are far more show than go.

Foul-mouthed Game Will Get You In Trouble

[Fridgehead] modified his Simon Says game to include a dirty word for each lighted button. This is a real good way to teach kids to swear and to get child protective services to pay you a visit all at the same time. The hardware has been modified to use an Arduino in tandem with an ISD audio chip. These chips can record and playback sound. Although [Fridgehead] could have made it say anything he, choose four words you won’t say in front of your mother. We should warn you not to play the video after the break if you’re at work or it’ll be your boss that comes after you, not your disappointed mom.

Continue reading “Foul-mouthed Game Will Get You In Trouble”