Research Area


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


Defense Against Adversarial Images using Web-Scale Nearest-Neighbor Search

This paper studies an approach that aims to make image-recognition systems robust against adversarial images by performing nearest-neighbor searches for similar images in a web-scale database of billions of unlabeled images.


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.


Retrieval-Augmented Convolutional Neural Networks for Improved Robustness Against Adversarial

This paper aims to make image-recognition systems robust against adversarial images by augmenting convolutional-network predictions with image retrieval.


Déjá Vu: An Empirical Evaluation of the Memorization Properties of ConvNets

The paper studies to what extent convolutional networks memorize the images they are trained on, and develops approaches to increase the differential privacy of these networks.


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.

Join Us

Tackle the world's most complex technology challenges.

Join Our Team

Latest News

Visit the AI Blog for updates on recent publications, new tools, and more.

Visit Blog