Scania • Södertälje • Heltid
Detta jobb är inaktivt och går inte att söka längre.
Scania is one of the world’s leading manufacturer of trucks and buses for heavy transports, as well as industrial and marine engines. Transport services and logistics services make up an increasing part of our business, which guarantees Scania’s customers cost-efficient transport solutions and high availability. Over a million Scania vehicles are in active use, in over 100 countries.
In the Connectivity section within Scania R&D, we develop new solutions for connected vehicles in our Internet of Things (IoT) platform, as part of Scania’s increasing focus on communication, services and smart transport solutions. Advanced data analysis capabilities are a cornerstone enabler in this development.
A recent trend in the field of edge AI is to utilize the power of the rich data. Federated learning (FL)  was one among them, which has thought to provide more privacy to the user as data never leaves the clients devices. The recent studies have shown previous said FL setting is not as secure as expected and targeted attacks can reveal information from certain clients . Scania as a manufacturer, has huge responsibility to ensure system resilience against attacks. With regulations such as GDPR, it is more and more vital to build a secure systems. This thesis will explore the possibilities of utilizing secure aggregation and differential privacy to build more secure federated learning in automotive setting, where the impact of these methods on communication cost and accuracy are also important.
The project will utilize a huge corpus of Scania’s recorded sensor logs. The student will have access to Scania’s cluster computers to train and run their models.
 Brendan McMahan, H., et al. "Communication-efficient learning of deep networks from decentralized data." ArXiv e-prints (2016): arXiv-1602.
 Hitaj, Briland, Giuseppe Ateniese, and Fernando Perez-Cruz. "Deep models under the GAN: information leakage from collaborative deep learning." Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security. 2017.
Description of the assignment
If time permits,
Assign education, line or direction: Masters programmes in Machine Learning, Data Science, Computer Science, Engineering Physics, Engineering Mathematics, Complex Adaptive Systems or similar.
Number of students: 1-2
Start date for the Thesis project: Anytime during fall 2021 or spring 2022
Estimated timescale: 20 weeks
Contact person and supervisor
Abhishek Srinivasan, Data Scientist, 08-553 816 96, firstname.lastname@example.org
Katarina Prytz, group manager, 08-553 723 08, email@example.com
Your application should contain the following:
As part of your application, please describe methods you may use or a suggested approach you might take to solve this problem.
Date of publication, as from – through
Until 2021-06-27. Applicants will be assessed on a continuous basis until the position is filled.
Scania is a world-leading provider of transport solutions, including trucks and buses for heavy transport applications combined with an extensive product-related service offering. Scania offers vehicle financing, insurance and rental services to enable our customers to focus on their core business. Scania is also a leading provider of industrial and marine engines. In 2019, we delivered 91,700 trucks, 7,800 buses as well as 10,200 industrial and marine engines to our customers. Net sales totalled to over SEK 152 billion, of which about 20 percent were services-related. Founded in 1891, Scania now operates in more than 100 countries and employs some 51,000 people. Research and development are concentrated in Sweden, with branches in Brazil and India. Production takes place in Europe, Latin America and Asia, with regional production centers in Africa, Asia and Eurasia. Scania is part of TRATON SE.