Projets novateurs réalisés

Explorez des milliers de projets réussis issus de la collaboration entre organisations et talents postsecondaires.

30156 projets achevés

2861
AB
5059
C.-B.
812
MB
673
NL
842
SK
8957
ON
9368
QC
96
PE
579
NB
1120
NS

Projets par catégorie

Command and Control Automation and Reporting

A red team is a group of cybersecurity experts who are tasked with simulating real-world attacks on an organization’s systems and networks. They do this by using a variety of tools and techniques to identify vulnerabilities and weaknesses in an organization’s defenses. This project implements command-and-control infrastructure, which is critical for the red team or simulated attackers to remotely control systems compromised by them and receive stolen data from the compromised systems.

Voir la description complète du projet
Superviseur du corps professoral :

Xiaodong Lin

Étudiant :

Partenaire :

Lares LLC

Discipline :

Computer science

Secteur :

Professional, scientific and technical services

Université :

University of Guelph

Programme :

Accelerate

Automating Insider Threat monitoring and detection

Insider threat involves individuals who have access to company resources and causes harm to the institution. These insiders can be employees, consultants, contractors, and third-party companies. Different types of insiders include people who intentionally harm the company, those to masquerade as a trusted entity, and those who unintentionally cause harm. Insider threats can lead to the disclosure, alteration, or destruction of sensitive information. To defend against such threats, companies need a system to detect and reduce insider threat risk. This project focuses on developing a system that automates the identification of high-risk groups for insider threats and generating remediation strategies for each risk a group may pose. The project will benefit EQ Bank’s Insider risk team in categorizing and identifying key hallmarks of insiders. This will provide more context to the team in making strategies to mitigate the risk emerging from potential insiders.

Voir la description complète du projet
Superviseur du corps professoral :

Ali Dehghantanha

Étudiant :

Partenaire :

Equitable Bank

Discipline :

Computer science

Secteur :

Finance and Insurance

Université :

University of Guelph

Programme :

Accelerate

Optimizing Security Orchestration, Automation, and Response for Incident response

This research project aims to develop cost-effective solutions to aid organizations in defending against cyber-attacks. With limited resources, security operations centers are struggling to defend against the vast volume of cyber-attacks. The project proposes reducing the work effort and amount of labor needed to perform tasks such as manual inspection and incident responses. By enhancing the functionality of current plugins and developing new ones for the Security Orchestration, Automation, and Response tool, cybersecurity experts will spend less time monitoring and more time implementing better security metrics, resulting in a more secure system and organization. The project’s expected benefit to partner organizations is a reduction in the cost of services and improved cybersecurity measures, resulting in fewer cyber-attacks and better protection for both the organization and its clients.

Voir la description complète du projet
Superviseur du corps professoral :

Rozita Dara

Étudiant :

Partenaire :

ISA Cybersecurity

Discipline :

Computer science

Secteur :

Professional, scientific and technical services

Université :

University of Guelph

Programme :

Accelerate

Monitoring and optimizing environmental conditions for improved CEA productivity

Consistent plant production is critical for plant product quality and marketability. Plant quality (leafy greens, cannabis or other plants) is influenced by the plant species/cultivar and environmental conditions (temperature, relative humidity, light level, light quality, CO2 levels, water quality and quantity, nutrient levels and air movement). Understanding existing variability of the environmental conditions is critical for any plant production operation with the knowledge quantified in one location transferrable to other locations. The objective of this study is to evaluate and monitor the environmental conditions in a CEA operation and modify existing sensor systems to understand temporal and spatial variability.

Voir la description complète du projet
Superviseur du corps professoral :

Mark Lefsrud

Étudiant :

Partenaire :

Fermes Urbaines Ôplant

Discipline :

Engineering

Secteur :

Agriculture

Université :

McGill University

Programme :

Accelerate

Adversarial Threats on a Penetration Testing Solution

Malicious adversaries are increasingly aiming to bypass security controls. There is a race to “owning” vulnerable machines and it is advantageous to malicious adversaries if the existing vulnerabilities are not patched. The research will be performed on a vulnerability assessment and management platform, specifically designed to assist organizations in identifying and mitigating cyber risks. It is unclear how effective the solution is against malicious insiders. For instance, in an enterprise environment, a malicious insider may circumvent the alerts that the platform may generate if it has taken over that machine. The research will focus on testing exploit techniques that can allow a threat actor to bypass the platform’s detection mechanisms and establish malware and persistence mechanisms within the target. By taking this approach, the project aims to identify the susceptibility of the platform to insider attacks and develop strategies to address them before malicious actors can exploit them. Proactively identifying and mitigating potential cyber threats is critical in today’s digital landscape, and this research can help organizations better understand and address their vulnerabilities.

Voir la description complète du projet
Superviseur du corps professoral :

Hassan Khan

Étudiant :

Partenaire :

Fiera Capital

Discipline :

Computer science

Secteur :

Finance and Insurance

Université :

University of Guelph

Programme :

Accelerate

Threat actor group profiling

Understanding the current panorama of threat actor groups worldwide is critical to building efficient cybersecurity programs. Information about threat actor groups’ motivations, tools, tactics and techniques they use to attack, and the type of targets they have in their sights provide valuable information to cybersecurity teams. To achieve this goal is essential to generate intelligence processing such information. Unfortunately, humans cannot process the amount of data generated daily, so implementing machine learning models is required for data processing and categorizing threat actor groups. With the proper profiling of threat actor groups, cybersecurity teams will strengthen their policies, security controls and processes, efficiently targeting their resources to threats that could impact them instead of wasting resources on pointless activities.

Voir la description complète du projet
Superviseur du corps professoral :

Charlie Obimbo

Étudiant :

Partenaire :

eSentire

Discipline :

Computer science

Secteur :

Cyber Security; Information and Communications Technology; Technology

Université :

University of Guelph

Programme :

Accelerate

Towards Fully Automated Tumor and Organ-at-Risk Detection and Segmentation from PSMA PET and SPECT Scans of Prostate Cancer Patients

Prostate cancer is the third deadliest cancer in men and early detection is crucial. PSMA is a protein that is highly present in prostate cells, making it a promising target for imaging and treatment. Total metabolic tumor volume (TMTV) is a measure of tumors’ characteristics, but it is currently not measured in clinical settings due to the labor-intensive and time-consuming process of manually delineating the borders of all tumors in PET images. AI can automate this process, but it struggles with low-quality images and small tumors. Our proposal is to develop AI-based object detection methods to locate lesions before segmenting them to improve accuracy. PSMA can also be used for personalized radioligand therapy, where radioactive drugs attached to PSMA molecules are injected into the patient to kill cancer cells. AI can aid in automating the process of manually delineating the borders of tumors and organs at risk in PET images, simplifying existing protocols, and predicting patient response and outcome. Personalized radioligand therapy could maximize cancer irradiation while minimizing toxicity to healthy organs, leading to better efficacy.

Voir la description complète du projet
Superviseur du corps professoral :

Arman Rahmim

Étudiant :

Partenaire :

Microsoft Canada Development Centre

Discipline :

Life Sciences

Secteur :

Technology; Health and Related Sciences & Technology; Artificial Intelligence

Université :

The University of British Columbia

Programme :

Elevate

Pondération dynamique de modèles prédictifs à court terme de la charge sur le réseau électrique du Québec

Le projet vise a developper des strategies permettant de combiner plusieurs modeles d’intelligence artificielle (IA) etudies au
sein de l’ecosysteme d’intelligence artificielle de l’equipe de prevision de la demande de !’unite prevision des apports et de la demande d’Hydro-Quebec. Ces modeles combines permettront d’obtenir de meilleures predictions a court terme de la charge
sur le reseau electrique du Quebec. Un premier outil sera developpe et valide au sein de plusieurs experiences IA temps reel, en vue de permettre de qualifier en condition reelle d’exploitation les modeles IA actuels et futurs qui iront en production, ainsi que les strategies d’entrainement et de ponderation dynamique, en plus d’orienter en parallele les axes de modernisation de la production.

Voir la description complète du projet
Superviseur du corps professoral :

Fabian Bastin

Étudiant :

Partenaire :

Hydro-Quebec

Discipline :

Engineering

Secteur :

Energy and Utilities; Technology; Green/Alternative Energy

Université :

Université de Montréal

Programme :

Accelerate

Increasing Grid Resilience using Game-theoretic Demand Side Management

Demand Side Management is a scheme that manages production, consumption and storage of energy of an aggregation of households in a neighborhood. The automated algorithms communicate between households to ensure that grid constraints are respected and households use energy optimally to maximize the use of green energy and save money. A promising tool for these control algorithms is game theory which gives mathematical guarantees for fairness and equity between households such that all participants in this scheme are treated equally while respecting their individual preferences. Game-theoretic control algorithms in the area of energy management are novel and have not been applied to real-world settings. One major hindrance of the implementation in the real world is that currently there are no safety and stability guarantees for these types of algorithm. In this project we want to develop such mathematical guarantees for a specific game-theoretic controller which is ideally suited for the Demand Side Management application.

Voir la description complète du projet
Superviseur du corps professoral :

Dominic Liao-McPherson

Étudiant :

Partenaire :

ETH Zurich

Discipline :

Engineering

Secteur :

Education

Université :

The University of British Columbia

Programme :

Globalink Research Award

Controllable and editable character performance using Implicit Neural Representation approaches

Nowadays, many of the movie characters whose performances move us on screen are at least in part digital. From superhero stunts to de-aged beloved actors and actresses, visual effects artists have to create digital characters and painstakingly reproduce performances to convince audiences. New Deep Learning (DL) technologies are emerging to help alleviate the processes. For instance, Deep Fakes have been quite successful at swapping facial performances. Other promising approaches are emerging under the large umbrella of Implicit Neural Representation (INRs) such as Neural Radiance Fields (NeRFs). We wish to explore novel ways to automate parts of the workflows involved in creating so-called Digital Doubles using NeRF-like algorithms.

Voir la description complète du projet
Superviseur du corps professoral :

David Lindell

Étudiant :

Partenaire :

DNEG

Discipline :

Computer science

Secteur :

Information and cultural industries

Université :

University of Toronto

Programme :

Accelerate

Exploration of RL-based agents in the context of space robotic systems

This research will explore machine learning methods in order to devise a control scheme for robotic manipulators(Candarm3) in the context of space exploration. The objective is to develop an early prototype for an autonomous learning agent which can carry out standard control tasks without any operator supervision.
The primary machine learning methods that will be studied will revolve around deep-reinforcement learning methods, in which an agent iteratively improves its performance in a given task. This is done through simulating training exercises, where the agent is rewarded for performing well. The agent modifies its behaviour in order to maximize its expected reward in future training exercises.

Voir la description complète du projet
Superviseur du corps professoral :

Chi-Guhn Lee

Étudiant :

Partenaire :

MacDonald, Dettwiler and Associates Inc (Brampton, ON)

Discipline :

Computer science

Secteur :

Manufacturing; Professional, scientific and technical services

Université :

University of Toronto

Programme :

Accelerate

Développement d’outils d’évaluation, de suivi et de mesures de la maturité et de la transformation numérique au sein des PME

Videns accompagne actuellement plusieurs PME dans le secteur de l’assurance dans leur initiative de transformation numérique. Nos services d’accompagnement visent à soutenir les PME dans leurs démarches vers une transformation numérique répondant à leurs besoins et alignée à leurs objectifs stratégiques.
L’accompagnement de Videns est divisé en 4 volets : l’analyse de la situation actuelle, l’évaluation du potentiel de transformation numérique, la planification et la création d’une feuille de route détaillée, et l’accompagnement pour la mise en oeuvre des solutions identifiées. Les 4 volets ont lieu sur une durée de 4 mois et ont pour but d’uniformiser les pratiques en matière d’accompagnement des PME. L’objectif final est de contribuer à la création et à la mise en place d’outils d’évaluation et de mesure standards pour aider les PME dans leur transformation numérique.

Voir la description complète du projet
Superviseur du corps professoral :

Ryad Titah

Étudiant :

Partenaire :

Videns Analytics

Discipline :

Computer science

Secteur :

Information and cultural industries; Professional, scientific and technical services

Université :

HEC Montréal

Programme :

Accelerate

Précédent
1...968969970971972973974...2,513
Suivant

Joignez-vous à un écosystème d’innovation florissant.

Abonnez-vous à notre infolettre dès maintenant!

S’inscrire