It’s that simple to spy on you: this tool guesses what you write just by listening to the noise of your keyboard



Share

The system is not capable of transcribing entire texts, but stealing login credentials is a piece of cake.

Internet security is a crucial aspect that we all must take into account. Hackers always find a way to penetrate the most complex security systems, which is why sometimes cracking your password can be as easy as taking candy from a child. Many times Internet criminals access sensitive information by taking control of computers, but in reality they don’t even need that to get it.

The Keytap3 tool knows which keys you press simply by listening to the sound of your keyboard

A young man named Georgi Gerganov has managed to create a tool capable of “listening” to how you type on your keyboard and deciphering the message based on the sound of the keys. To achieve this, it only needs access to your microphone, the keyboard might even be offline.



Gerganov has been refining this technology for a long time, and narrating his experience through his YouTube channel. At first he managed to a system listen to the sound of the keys and interpret words, but it had many limitations. He called it Keytap, but to identify the message, the sound of the keys had to be clear and the microphone had to be static at all times. With the new version of Keytap3, that has changed.

A tool that “hears” you write and is capable of decoding the message

This more refined version of the program is capable of interpreting the message without the need for a static microphone. It still requires the use of a mechanical keyboard (which are the loudest and easiest to interpret), but the volume of the keys does not have to be as loud as before. The system it works with some phrases that it takes as reference to translate what you “hear” into text.

In this version you still can’t transcribe messages with complete accuracy, but you can recognize words based on references. If you’ve heard the word “password” before, you can easily identify it if you’re typing it on the keyboard. This is perfect for detect keywords in loginsand allows you to blatantly steal personal information without having access to the computer, only to the microphone.

On Georgi Gerganov’s website you can try a demo of how the system works. If you have a mechanical keyboard and microphone, you can try typing a text in English and see if the system is able to transcribe it. You won’t get a full text, but yes a breakdown of words you used in the message.

At the moment Gerganov is making the development of his tool public, but not everyone is equally transparent. We recommend that never give apps permissions you don’t think they should haveand be very careful when entering login credentials on networks or websites that you are not used to.

Related topics: Technology

Share



Related News

PC death: Chip maker Intel ‘plans to lay off thousands of employees’ as rising popularity of smartphones and tablets dampens demand for traditional computers

Chipmaker Intel is reportedly planning major layoffs, which could number into the thousands, in the face of a slowdown in the personal computer market.

Countries with the Best Internet Service Announced

BroadbandChoices, the latest Internet Accessibility Index in the report published his research results based on metrics such as download and upload speed,

Get the Accessories That Power Your Gadgets with the Best Prime Days Deals on Anker Products

We love Anker's products. Not only does the company offer incredible accessories to complement our daily drivers like our smartphones and laptops, but they

Converting a Twitter thread to a PDF is that simple

Did you find a thread on Twitter interesting and want to have it saved in a PDF document? You don't need to copy it manually, because exists a tool that

Thermal cameras and AI can be used to crack passwords, new study warns

A password might not be enough to protect a device from hackers. A new study has shown how criminals can use thermal cameras to retrieve passwords typed in by

Tensor G2 confirmed as 5nm processor, not 4nm as expected

As per the new information, the Tensor G2 is actually built on a 5nm manufacturing process and not a 4nm one as was expected before the launch.