RESEARCH AREA

Integrity

We develop technologies to keep people safe on social network platforms and connect people to what matters most to them. This means investing broadly in the areas of Natural Language Processing, Computer Vision, and Machine Learning - specifically multilingual/multimodal understanding, misinformation, tampering, entity detection, and semi-supervised learning.

Latest Publications

June 15, 2019

INTEGRITY

Feature Denoising for Improving Adversarial Robustness

This paper develops an approach that makes image-recognition systems robust against adversarial images by introducing a novel feature-denoising layer in convolutional networks, and training these networks using adversarial training. The work described in this paper formed the basis for our winning entry in the CAAD Adversarial Image Defense Competition 2018.

June 15, 2019

April 30, 2018

INTEGRITY

Countering Adversarial Images using Input Transformations

The paper studies approaches that make image-recognition systems more robust against adversarial images by applying pre-processing transformations on the input images.

April 30, 2018