Deep Neural Network are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Anh Nguyen, Jason Yosinski, Jeff Clune
Deep neural networks (DNNs) have recently been achieving state-of-the-art performance on a variety of pattern-recognition tasks, most notably visual classification problems. Given that DNNs are now able to classify objects in images with near-human-level performance, questions naturally arise as to what differences remain between computer and human vision. A recent study (Szegedy et al, 2014) revealed that changing an image (e.g. of a lion) in a way imperceptible to humans can cause a DNN to label the image as something else entirely (e.g. mislabeling a lion a library). Here we show a related result: it is easy to produce images that are completely unrecognizable to humans, but that state-of-the-art DNNs believe to be recognizable objects with 99.99% confidence (e.g. labeling with certainty that white noise static is a lion). Specifically, we take convolutional neural networks trained to perform well on either the ImageNet or MNIST datasets and then find images with evolutionary algorithms or gradient ascent that DNNs label with high confidence as belonging to each dataset class. It is possible to produce images totally unrecognizable to human eyes that DNNs believe with near certainty are familiar objects, which we call “fooling images” (more generally, fooling examples). Our results shed light on interesting differences between human vision and current DNNs, and raise questions about the generality of DNN computer vision.
Conference: CVPR 2015. Oral presentation (3.3% acceptance rate)
- Community Top Paper Award (among 3 out of 2103 papers to be awarded)
- 63rd most influential paper worldwide in 2015 via AltMetric.
- Best Long Research video & Most Educational Research video at IJCAI 2015
- Best Research video at AAAI 2016
A 5-min video summary of the paper.
More info: including FAQs here