ServiceNow Research

Adversarial Learning

Adversarial Functionality-Preserving Training in the Malware Domain
Workshop at the Neural Information Processing Systems (NeurIPS),  2019.
Cite
On Adversarial Mixup Resynthesis
On Adversarial Mixup Resynthesis
In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders. We …
Conference on Neural Information Processing Systems (NeurIPS),  2019.
PDF Cite Code
Physical Adversarial Textures that Fool Visual Object Tracking
Physical Adversarial Textures that Fool Visual Object Tracking
We present a system for generating inconspicuous-looking textures that, when displayed in the physical world as digital or printed …
International Conference on Computer Vision (ICCV),  2019.
PDF Cite
Adversarial Computation of Optimal Transport Maps
Adversarial Computation of Optimal Transport Maps
Computing optimal transport maps between high-dimensional and continuous distributions is a challenging problem in optimal transport …
ArXiv,  2019.
PDF Cite Code
Adversarial Learning of General Transformations for Data Augmentation
Adversarial Learning of General Transformations for Data Augmentation
Data augmentation (DA) is fundamental against overfitting in large convolutional neural networks, especially with a limited training …
Workshop at the International Conference on Learning Representations (ICLR),  2019.
PDF Cite Code
Adversarial Mixup Resynthesizers
Adversarial Mixup Resynthesizers
In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders. We …
Workshop at the International Conference on Learning Representations (ICLR),  2019.
PDF Cite Code
Semantics Preserving Adversarial Learning
Semantics Preserving Adversarial Learning
While progress has been made in crafting visually imperceptible adversarial examples, constructing semantically meaningful ones remains …
ArXiv,  2019.
PDF Cite
Adversarial Framing for Image and Video Classification
Adversarial Framing for Image and Video Classification
Neural networks are prone to adversarial attacks. In general, such attacks deteriorate the quality of the input by either slightly …
Student Abstract at the Association for the Advancement of Artificial Intelligence (AAAI),  2019.
PDF Cite Code
Towards Text Generation with Adversarially Learned Neural Outlines
Towards Text Generation with Adversarially Learned Neural Outlines
Recent progress in deep generative models has been fueled by two paradigms – au- toregressive and adversarial models. We propose a …
Conference on Neural Information Processing Systems (NeurIPS),  2018.
PDF Cite
Adversarially-Trained Normalized Noisy-Feature Auto-Encoder for Text Generation
Adversarially-Trained Normalized Noisy-Feature Auto-Encoder for Text Generation
This article proposes Adversarially-Trained Normalized Noisy-Feature Auto-Encoder (ATNNFAE) for byte-level text generation. An ATNNFAE …
ArXiv,  2018.
PDF Cite