Adversarial Learning
We propose Adaptive Diffusion Denoised Smoothing, a method for certifying the predictions of a vision model against adversarial …
In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders. We …
We present a system for generating inconspicuous-looking textures that, when displayed in the physical world as digital or printed …
Computing optimal transport maps between high-dimensional and continuous distributions is a challenging problem in optimal transport …
Data augmentation (DA) is fundamental against overfitting in large convolutional neural networks, especially with a limited training …
In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders. We …
While progress has been made in crafting visually imperceptible adversarial examples, constructing semantically meaningful ones remains …
Neural networks are prone to adversarial attacks. In general, such attacks deteriorate the quality of the input by either slightly …
Recent progress in deep generative models has been fueled by two paradigms – au- toregressive and adversarial models. We propose a …
This article proposes Adversarially-Trained Normalized Noisy-Feature Auto-Encoder (ATNNFAE) for byte-level text generation. An ATNNFAE …