AI Technology & Industry Review
Rather than attempting to defend convolutional networks against them, the researchers introduce a novel enhanced adversarial training scheme, AdvProp, which treats adversarial examples as additional training examples to improve the accuracy of image classification models.
Although convolutional neural networks have reached Superman level on image classification tasks, adversarial examples remain the kryptonite that can mysteriously defeat even SOTA models.
Now a group of researchers from the Seattle-based Allen Institute for Artificial Intelligence (AI2) have shown how trigger words and phrases can “inflict targeted errors” on natural language processing (NLP) model outputs, prompting them to generate racist and hostile content.
To ramp up the robustness of neural networks, researchers from OpenAI have introduced a novel method that evaluates how well a neural network classifier performs against adversarial attacks that were not seen during their training.
Researchers have proposed a new adversarial attack approach, SemanticAdv, which generates adversarial perturbations by manipulating not pixels but rather an image’s semantic attributes.
Researchers from UC Berkeley and the Universities of Washington and Chicago have released a set of natural adversarial examples, which they call “ImageNet-A.”
Researchers from Technische Universität Wien, Austria, and Politecnico di Torino, Italy, explored adversarial attacks on Capsule Networks, proposing an algorithm which automatically generates targeted adversarial examples in black-box attack scenarios.
n the new paper Adversarial Examples Are Not Bugs, They Are Features, a group of MIT researchers propose that adversarial examples’ effectiveness can be attributed to non-robustness: “Adversarial vulnerability is a direct result of our models’ sensitivity to well-generalizing features in the data.”
Machines have already beaten humans in image recognition accuracy, but they are also susceptible to errors. Last Friday, Vietnamese company Bkav announced they had outsmarted the AI-powered image recognition machine that unlocks the new iPhone X.