ML security

What if you wanted to make a self-driving car stop in the middle of the highway? Sounds impossible? Let’s see....

Adversarial Patches are increasingly common attacks on AI models. But how easy are they to set up? In this article,...

Adversarial Examples are increasingly common attacks on AI models. But how easy are they to set up? In this article,...

Did you know that a simple sticker on a STOP sign is sufficient to fool a self-driving car? Why? Because...

Google Photos is one of the most widely-used photo management applications globally, pre-installed on almost every Android device running Google...

As deep learning (DL) models become integral to application functionality, protecting them is more important than ever. In this article,...

Artificial Intelligence (AI) powers a wide range of modern technologies — from autonomous vehicles to facial recognition systems. Every AI...

AI models are everywhere—from unlocking your phone to powering medical diagnostics. But few realize how exposed these models become once...

Machine learning models are the results of highly complex computations and optimization over a massive amount of data. Data is...

Model inversion attacks pose a real threat to machine learning models trained on sensitive data — from industrial secrets to...

On-Device Artificial Intelligence (AI) is an invaluable asset to many industries, offering revolutionary capabilities in analysis and prediction. But with...

This post introduces the research of Thibault Maho, a Ph.D. student working on the security of neural networks. His work...