Stealing data from keystrokes recorded over Zoom with 93% accuracy
This post is references an external article or page. Consider it a bookmark, and in no way an endorsement of the article, author, or website. I frequently bookmark content I disagree with.
🔗 via bleepingcomputer.com.
Highlights
A team of researchers from British universities has trained a deep learning model that can steal data from keyboard keystrokes recorded using a microphone with an accuracy of 95%.
When Zoom was used for training the sound classification algorithm, the prediction accuracy dropped to 93%, which is still dangerously high, and a record for that medium.
- Researchers have developed a deep learning model, with 95% accuracy, that can extract data from keyboard keystrokes recorded by a microphone and 93% when recorded on Zoom.
- The attack process involves recording keystrokes, creating waveforms and spectrograms from recordings, and training an image classifier on these images. The setup used a MacBook Pro laptop, an iPhone 13 mini, and Zoom.
Researchers have developed a deep learning model, with 95% accuracy, that can extract data from keyboard keystrokes recorded by a microphone and 93% when recorded on Zoom.
This paper introduces a method for obtaining secret keys from a smart card reader by analyzing video footage of its power LED, exploiting changes in brightness due to CPU power consumption.
This paper demonstrates an attack where the regular receipt of SMS messages allows an attacker to infer the recipient’s location using the timing of the message send and receipt.
Many cities are implementing dystopian surveillance to tackle crime. But, as Russia has shown since the Ukraine war, surveillance is an irresistible tool when the going gets tough.
Researchers at Carnegie Mellon have found a new way to locate and map people in space using WiFi transmitters. Or, x-ray vision into people’s homes.
Very imaginative ruminations on the future of AI. The articulation of our future super powers is particularly interesting.
This Hacker News user is demonstrating how easily you can find people’s anonymous accounts by comparing writing styles.
Some basic advice for keeping anonymous online. Since some high profile data leaks in Australia, I’ve been thinking a lot about just how much data various businesses and services demand from users.
No matter how privacy or security conscious you are, if the people you are messaging are laissez-faire, your data is at risk. No matter how careful you are with your Facebook account, for instance, if someone you are messaging has their account compromised, your messages with them are also compromised.
A creepy example of how easy it is to identify people using security camera footage.
We need to move away SMS-based multi-factor authentication and eventually passwords all together. It’s encouraging to see Passkeys have already been adopted by the likes of PayPal.
ToS;DR is a resource that collates TL;DR summaries of various terms of service so you don’t have to read the fine print.