Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
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 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.
Code (2)
Tasks
Evolutionary AlgorithmsSimilar Papers 제목 키워드 기반
Generating Minimal Adversarial Perturbations with Integrated Adaptive Gradients
Deep neural networks are easily fooled high confidence predictions for adversarial samples
Image ClassificationConfidence estimation in Deep Neural networks via density modelling
State-of-the-art Deep Neural Networks can be easily fooled into providing incorrect high-confidence predictions for images with small amounts of adversarial noise. Does this expose a flaw with deep neural networks, or do…
Can AI Detect Life? Lessons from Artificial Life
Modern machine learning methods have been proposed to detect life in extraterrestrial samples, drawing on their ability to distinguish biotic from abiotic samples based on training models using natural and synthetic orga…
Are DNNs fooled by extremely unrecognizable images?
Fooling images are a potential threat to deep neural networks (DNNs). These images are not recognizable to humans as natural objects, such as dogs and cats, but are misclassified by DNNs as natural-object classes with hi…
Out-of-Distribution DetectionEvaluation Methodology for Attacks Against Confidence Thresholding Models
Current machine learning algorithms can be easily fooled by adversarial examples. One possible solution path is to make models that use confidence thresholding to avoid making mistakes. Such models refuse to make a predi…
Adversarial RobustnessBenchmarking