Machine learning security is extraordinarily difficult because the attacks are so varied—and it seems that each new one is weirder than the next. Here’s the latest: a training-time attack...
Read moreRecovering Passwords by Measuring Residual Heat
October 12 2022Researchers have used thermal cameras and ML guessing techniques to recover passwords from measuring the residual heat left by fingers on keyboards. From the abstract:
We detail the implementation...
Read more
Move over Patch Tuesday – it’s Ada Lovelace Day!
October 11 2022Hacking on actual computers is one thing, but hacking purposefully on imaginary computers is, these days, something we can only imagine.
Read moreInserting a Backdoor into a Machine-Learning System
October 11 2022Interesting research: “ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks, by Tim Clifford, Ilia Shumailov, Yiren Zhao, Ross Anderson, and Robert Mullins:
Abstract: Early backdoor attacks against machine...
Read more
Interesting research: “Sponge Examples: Energy-Latency Attacks on Neural Networks“:
Abstract: The high energy costs of neural network training and inference led to the use of acceleration hardware such as...
Read more
Yet another adversarial ML attack:
Most deep neural networks are trained by stochastic gradient descent. Now “stochastic” is a fancy Greek word for “random”; it means that the training...
Read more
Undetectable Backdoors in Machine-Learning Models
April 19 2022New paper: “Planting Undetectable Backdoors in Machine Learning Models“:
Abstract: Given the computational cost and technical expertise required to train machine learning models, users may delegate the task of...
Read more
Using Radar to Read Body Language
March 8 2022Yet another method of surveillance:
Radar can detect you moving closer to a computer and entering its personal space. This might mean the computer can then choose to perform...
Read more
The crooks have shown that they're willing to learn and adapt their attacks, so we need to make sure we learn and adapt, too.
Read moreThe crooks have shown that they're willing to learn and adapt their attacks, so we need to make sure we learn and adapt, too.
Read more
Recent Comments