Jianhai Su

U of SC computing resource center supports[ Sylab.io](https://sylabs.io/), With that, we should be able to create a docker container, which gives us root privilege, and deploy it to the computing...

Detection as a defense

1

The idea is to differentiate BS and AE based on their output from distinct transform models. In [Detecing adversarial samples from artifacts.pdf](https://github.com/softsys4ai/adversarial_transformers/files/3530683/Detecing.adversarial.samples.from.artifacts.pdf), it is shown that different models make different...