Abstract: Due to the exponential disparity in the magnitude of high- and low-frequency components in the image frequency domain, existing frequency-domain enhancement methods for adversarial examples ...
Abstract: Even though thermostatically controlled loads like air conditioners present a great potential for providing ancillary services to the electric power grid, the practical challenges associated ...
Abstract: Recent studies have shown that Deep Neural Networks (DNNs) are easily deceived by adversarial examples, revealing their serious vulnerability. Due to the transferability, adversarial ...
Abstract: Deep neural networks are known to be susceptible to imperceptible adversarial perturbations. Many studies aim to interpret adversarial examples in the frequency domain. However, existing ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results