Security

Recent developments in Adversarial Example, Part I

As of mid-2017 there are already many proposals to fool DNNs by adversarial example. Papernot et al (2016) proposed so far the most powerful such attack against image classifiers by exploiting transferability. According to the experiments conducted, the method can achieve nearly 90% misclassification rates for DNNs services hosted on Amazon and Google. This practical Continue Reading