Efficient adversarial robustness evaluation of AI models with limited access

Thursday, January 31, 2019 - 08:30 in Mathematics & Economics

Recent studies have identified the lack of robustness in current AI models against adversarial examples—intentionally manipulated prediction-evasive data inputs that are similar to normal data but will cause well-trained AI models to misbehave. For instance, visually imperceptible perturbations to a stop sign can be easily crafted and lead a high-precision AI model towards misclassification. In our previous paper published at the European Conference on Computer Vision (ECCV) in 2018, we validated that 18 different classification models trained on ImageNet, a large public object recognition dataset, are all vulnerable to adversarial perturbations.

Read the whole article on Physorg

More from Physorg

Latest Science Newsletter

Get the latest and most popular science news articles of the week in your Inbox! It's free!

Check out our next project, Biology.Net