Original image

Forget Your Password: Typing Rhythm and Computer Security

Original image

Patricia Loring, a research associate at Carnegie Mellon University, presses tiny blue dots on my fingers and the back of my hand. She tells me to adjust the keyboard as she maneuvers three webcams. On a monitor, I see a split screen, displaying images of my hands and posture (which is terrible). The blue stickers make it easier for the cameras to record my finger movements.

She tells me to look at a picture, Norman Rockwell’s Girl with Black Eye, and compose an email about it. I must type uninterrupted until I fill a text box, which probably holds about 400 words. I cannot talk and she tells me to not worry about my grammar or errors.

I am typing as a participant in a study led by Roy Maxion, a PhD research professor of computer science at CMU. He thinks that typing rhythms and the timing of keystrokes might be able to be used as a biometric, adding another level of security to computers. Keystroke biometrics could also be used in criminal cases.

Computer scientists have known about keystroke biometrics for years, but the research has been conducted in a haphazard way. Maxion is taking a fresh look. If the theories are correct, each person’s typing rhythm is different. Nobody could mimic another person's rhythm.


Since the 1800s and the rise of the telegraph, there has been evidence that each individual possesses a unique typing style.

“The original idea came from the 1800s with the telegraph—one person could tell who was on the other end of the line because of the rhythm of the dots and dashes,” Maxion says.

During World War II, telegraph operators transmitted covert messages using Morse code. While each side used encrypted messages, the British still listened to the German cables and soon discovered they could identify certain telegraph operators by their typing rhythms, what telegraph operators (and ham radio aficionados) refer to as an operator’s fist. After realizing what operator was attached to what battalion, the British could track the German troop movement—even though they didn’t understand the messages.

In the 1970s, a researcher with the Rand Corporation produced a small study on keystroke rhythms. The researcher looked at six different typists, noticing each one had a different tempo and he could identify each by their typing beat. In the following decades, researchers replicated the studies, but sometimes there were too many variables. For example, some researchers ask participants to log into a site from their home computer to type, but this presents a problem. “Everyone has a different keyboard so you don’t know if the keyboard influences typing,” Maxion explains. (The keyboard in Maxion’s lab felt tight, which probably slowed my typing.)

Typing Tests

Maxion conducts a variety of different experiments to determine typing rhythm. In one set, he asked a number of subjects to come to the lab and learn a password, which is 10 characters long. At first, all the subjects struggle to learn the string of characters, but soon they do, a pattern emerges—each person’s beat is different. Of 28 people typing the 10-character passwords, Maxion can identify typists with 99.97 percent accuracy. Even though this is an incredibly low error rate, Maxion feels he cannot say with certainty that everyone has a unique typing style.

“Our own work would suggest that keystrokes are unique,” Maxion says. But he adds a caveat: “The more people, the more likely that two people’s typing rhythms will be too similar to tell them apart.”

By including an individual’s typing rhythm as an additional layer of protection, it makes it almost impossible for an imposter to access a computer from the keyboard login. “If you knew my password, you could access my computer,” he says. But it is exceedingly difficult (if not impossible) to mimic another’s typing cadence.

In the lab, as I typed an email to my mother about my fictitious redheaded child who'd gotten into a fight because a classmate called her a ginger, I was helping Maxion and Loring gather data for a different experiment—to see if a typist can be identified by her unique style as she types throughout the day, offering continuous re-authentication. In some high security jobs, it is important to prompt the user to re-identify herself to prevent imposters from accessing information or changing sensitive documents. This might also prove useful for prosecutors in white-collar crimes, where documents may have been altered.

After I finish weaving a tale about my imaginary offspring, Loring asks me to place my right hand on what looks like grid paper used in high school math classes. She positions my hands, spreading my fingers wider, asking me to keep my wrist straight. She snaps a picture. On to the left. My hands will join pictures of hundreds of others.

“Even the size of hands can influence keystrokes,” Maxion explains.

Loring tells me I'm a well-behaved typist—I show the hallmarks of someone who learned to type in a class. My typing teacher would be pleased.

For more information about Maxion’s research, check out his publications at

Original image
iStock // Ekaterina Minaeva
Man Buys Two Metric Tons of LEGO Bricks; Sorts Them Via Machine Learning
Original image
iStock // Ekaterina Minaeva

Jacques Mattheij made a small, but awesome, mistake. He went on eBay one evening and bid on a bunch of bulk LEGO brick auctions, then went to sleep. Upon waking, he discovered that he was the high bidder on many, and was now the proud owner of two tons of LEGO bricks. (This is about 4400 pounds.) He wrote, "[L]esson 1: if you win almost all bids you are bidding too high."

Mattheij had noticed that bulk, unsorted bricks sell for something like €10/kilogram, whereas sets are roughly €40/kg and rare parts go for up to €100/kg. Much of the value of the bricks is in their sorting. If he could reduce the entropy of these bins of unsorted bricks, he could make a tidy profit. While many people do this work by hand, the problem is enormous—just the kind of challenge for a computer. Mattheij writes:

There are 38000+ shapes and there are 100+ possible shades of color (you can roughly tell how old someone is by asking them what lego colors they remember from their youth).

In the following months, Mattheij built a proof-of-concept sorting system using, of course, LEGO. He broke the problem down into a series of sub-problems (including "feeding LEGO reliably from a hopper is surprisingly hard," one of those facts of nature that will stymie even the best system design). After tinkering with the prototype at length, he expanded the system to a surprisingly complex system of conveyer belts (powered by a home treadmill), various pieces of cabinetry, and "copious quantities of crazy glue."

Here's a video showing the current system running at low speed:

The key part of the system was running the bricks past a camera paired with a computer running a neural net-based image classifier. That allows the computer (when sufficiently trained on brick images) to recognize bricks and thus categorize them by color, shape, or other parameters. Remember that as bricks pass by, they can be in any orientation, can be dirty, can even be stuck to other pieces. So having a flexible software system is key to recognizing—in a fraction of a second—what a given brick is, in order to sort it out. When a match is found, a jet of compressed air pops the piece off the conveyer belt and into a waiting bin.

After much experimentation, Mattheij rewrote the software (several times in fact) to accomplish a variety of basic tasks. At its core, the system takes images from a webcam and feeds them to a neural network to do the classification. Of course, the neural net needs to be "trained" by showing it lots of images, and telling it what those images represent. Mattheij's breakthrough was allowing the machine to effectively train itself, with guidance: Running pieces through allows the system to take its own photos, make a guess, and build on that guess. As long as Mattheij corrects the incorrect guesses, he ends up with a decent (and self-reinforcing) corpus of training data. As the machine continues running, it can rack up more training, allowing it to recognize a broad variety of pieces on the fly.

Here's another video, focusing on how the pieces move on conveyer belts (running at slow speed so puny humans can follow). You can also see the air jets in action:

In an email interview, Mattheij told Mental Floss that the system currently sorts LEGO bricks into more than 50 categories. It can also be run in a color-sorting mode to bin the parts across 12 color groups. (Thus at present you'd likely do a two-pass sort on the bricks: once for shape, then a separate pass for color.) He continues to refine the system, with a focus on making its recognition abilities faster. At some point down the line, he plans to make the software portion open source. You're on your own as far as building conveyer belts, bins, and so forth.

Check out Mattheij's writeup in two parts for more information. It starts with an overview of the story, followed up with a deep dive on the software. He's also tweeting about the project (among other things). And if you look around a bit, you'll find bulk LEGO brick auctions online—it's definitely a thing!

Original image
Here's How to Change Your Name on Facebook
Original image

Whether you want to change your legal name, adopt a new nickname, or simply reinvent your online persona, it's helpful to know the process of resetting your name on Facebook. The social media site isn't a fan of fake accounts, and as a result changing your name is a little more complicated than updating your profile picture or relationship status. Luckily, Daily Dot laid out the steps.

Start by going to the blue bar at the top of the page in desktop view and clicking the down arrow to the far right. From here, go to Settings. This should take you to the General Account Settings page. Find your name as it appears on your profile and click the Edit link to the right of it. Now, you can input your preferred first and last name, and if you’d like, your middle name.

The steps are similar in Facebook mobile. To find Settings, tap the More option in the bottom right corner. Go to Account Settings, then General, then hit your name to change it.

Whatever you type should adhere to Facebook's guidelines, which prohibit symbols, numbers, unusual capitalization, and honorifics like Mr., Ms., and Dr. Before landing on a name, make sure you’re ready to commit to it: Facebook won’t let you update it again for 60 days. If you aren’t happy with these restrictions, adding a secondary name or a name pronunciation might better suit your needs. You can do this by going to the Details About You heading under the About page of your profile.

[h/t Daily Dot]