AI Tools Can Now Steal Passwords With 93% Accuracy By Listening To Your Keystrokes!

We invented passwords to secure our transactions, bank accounts and online privacy. Then we developed artificial intelligence to make human life easier. Yet, now we are looking at AI outsmarting not just us humans but also other technologies we invented to keep us safe!

Apparently, as per the latest study, an AI tool can steal passwords with 93% accuracy by listening to the keystrokes (the typing sounds) on online calls. Entering your passwords on a Zoom meeting can put you at risk of an AI-driven cyber-attack, as researchers have developed an AI model that can identify the use of specific keys by listening to the typing sound.

Furthermore, the accuracy rate reached up to 95% when the keystrokes were recorded using an iPhone 13 mini. (Maybe it is time we change our keyboard sound settings!)

The research was published as part of the IEEE European Symposium on Security and Privacy Workshops, with researchers associated with Durham University, the University of Surrey and the Royal Holloway University of London.

Source

If you are worrying about AI cyber-attacks, let’s hear from the authors and researchers themselves!
What were the highlights of the research?

"Acoustic side-channel attacks are a growing threat to keyboards,” the researchers said. Hackers have been using side-channel attacks to exploit the information – your system's power usage or the keystroke sound it makes – rather than attacking the system directly.
The developed AI tool was based on deep learning that trains computers to analyze days similar to how the human brain functions.
While the touch typing and background noise would lower the accuracy rate of the AI tool, the passwords containing full words hold the greatest risk of attack.
The authors also stated that these types of attacks are yet to be studied further. They also wrote about the mention of ‘acoustic emanations’ as a vulnerability in a 1982 partially declassified NSA document.

The study has discovered a few concerns regarding the unethical use of AI and how it can compromise security and privacy.

How can AI threaten security and privacy?

Al tools make it harder to detect scams because AI can personalize scams for each target. #Scary
The specialists have raised concerns about how the advancement of AI and 5G technology would highlight the vulnerabilities of internet-connected devices and increase overall cybersecurity threats.
Maryam Mehrnezhad, one of the study's authors and an associate professor at the Royal Holloway University of London, doesn't think the pressure to safeguard oneself should be on the end user. Instead, she suggested that the cybersecurity community should develop better solutions to enable citizens to use modern technologies without fear.

The advancements in AI have unfolded many opportunities without a doubt. However, we must also develop regulations to ensure the ethical use of AI.

What are your thoughts on this new type of potential cyber-risk? Do you think such studies will help us come up with better compliances for the use of AI technologies?

Share your thoughts in the comment section below!

First published on Fri, Aug 18, 2023

Enjoyed what you've read so far? Great news - there's more to explore!

Stay up to date with the latest news, a vast collection of tech articles including introductory guides, product reviews, trends and more, thought-provoking interviews, hottest AI blogs and entertaining tech memes.

Plus, get access to branded insights such as informative white papers, intriguing case studies, in-depth reports, enlightening videos and exciting events and webinars from industry-leading global brands.

Dive into TechDogs' treasure trove today and Know Your World of technology!

Disclaimer - Reference to any specific product, software or entity does not constitute an endorsement or recommendation by TechDogs nor should any data or content published be relied upon. The views expressed by TechDogs' members and guests are their own and their appearance on our site does not imply an endorsement of them or any entity they represent. Views and opinions expressed by TechDogs' Authors are those of the Authors and do not necessarily reflect the view of TechDogs or any of its officials. All information / content found on TechDogs' site may not necessarily be reviewed by individuals with the expertise to validate its completeness, accuracy and reliability.

Tags:

AI Tool Artificial Intelligence Keystrokes Researcher Cyber-attack Cybersecurity

Join The Discussion

Emerging Technology