Development of a microbiome relevant image-capture food analysis tool.

Phyla’s vision is to be the world’s first integrated solution for gut health through a digital health platform for those affected by Inflammatory Bowel Disease (IBD) and Irritable Bowel Syndrome (IBS). Phyla’s platform combines an at-home gut microbiome (intestinal bacteria) stool testing subscription and a mobile application for self-reported disease and lifestyle parameter tracking. It […]

Read More
Deep learning models for compound design

Traditional drug development strategy is costly, tiresome, and labor-intensive. In the last decade, artificial intelligence (AI) technologies have shown promising results to overcome some of these limitations. However, these computational technologies still cannot efficiently generate novel drugs with expected properties for treating specific diseases. Here we will apply new generation of AI frameworks to design […]

Read More
ChainCert platform: Verification of authenticity of certificates by exploiting hybrid Blockchain technologies

Blockchain is a well-known immutable, transparent and anti-counterfeit platform. As such it can be appropriate for submitting certificates for validation and safe-keeping. However, because of its requirements for complex and heavy computations for enhanced security and verification of each submission in the network, in this project, we will first study both public and private Blockchain […]

Read More
Augmentation de données et optimisation de l’espace latent d’un auto-encodeur variationnel (VAE) pour la détection de défauts et le pronostic des alternateurs hydrauliques

L’objectif du projet est d’automatiser la reconnaissance des signaux acoustiques et vibratoires d’une part, et des signaux de décharges partielles d’autres part, et ceci à l’aide d’un modèle d’apprentissage profond. Cette reconnaissance est la première étape du développement d’un modèle de pronostic et de suivi de l’évolution de la dégradation des alternateurs. Ces signaux sont […]

Read More
AI-enabled molecular search database

The project aims to facilitate the research and development of new drugs by applying machine learning and deep learning to further develop an AI-assisted molecular search database. The company has an internal dataset holding more than a billion molecules. Two main challenges are keeping the molecule catalog updated and Searching for the desired molecule or […]

Read More
Applying state-of-art NLP models to molecular representation

Molecular generative methods are at the heart of our computational platform. We use cutting edge deep neural networks in order to generate unseen molecules based on existing conditions or molecular space. Since external projects typically require different architectures, we are continuously expanding our generative methods toolbox with new approaches. This project aims to augment our […]

Read More
Portrait photo segmentation and generation with Deep Neural Network

In this project, the main purpose is to develop a tool for facial image anonymization by replacing the face in an image with a fake, generated face. To have realistic looking generated images, it is essential for the generated face to have a similar pose to the original one and to be seamlessly harmonic to […]

Read More
Object occlusion detection

Sometimes an object is partially hidden by a physical object like fingers, book etc. or by digitally pasted artifacts like blurringof an area. The intern will be working on detecting these types of digital and physical occlusions on an object. At Jumio we encounter documents that are hidden or occluded by such masks. These documents […]

Read More
Automation & Orchestration for Improved Security Communication

Speed is incredibly important when addressing issues with computer security. The longer the time between the attack’s start and resolution, the more assets that attackers can steal from a company. There are various security platforms that can alert a company to a cyber-attack. This research project aims to combine knowledge from all these platforms together […]

Read More
Anomalous DNS Query Detection Using Machine Learning Approaches

For organizations that use the Internet, their employees will visit thousands of websites every day. However, there is a chance that the destination website is not safe to visit. Such websites may be fraudulent, phishing, or even data-stealing related. On the other hand, determining if the target website link is suspicious or not could help […]

Read More
Cyber Threat Intelligence Integration with MISP Threat Sharing

In the recent technological age, new threats and attacks emerge nearly every day. It might be against everyone on the internet or targeted towards specific organizations and individuals. Attackers have begun to use highly sophisticated techniques and technologies to attain their objectives. It’s a high time, the defenders scale up to defending their infrastructure against […]

Read More