IFAP generates adversarial perturbations using model gradients and then shapes them in the discrete cosine transform (DCT) domain. Unlike existing frequency-aware methods that apply a fixed frequency ...

Although deep neural networks have achieved great success in many tasks, they encounter security threats and are often fooled by adversarial examples, which are created by making slight modifications ...

Start working toward program admission and requirements right away. Work you complete in the non-credit experience will transfer to the for-credit experience when you ...