Grupo COMIT

Ejemplos de instituciones con las que ha colaborado

Tesis doctoral en conjunto con la U. de Nice, en Francia.

Preserving privacy in deep learning networks

In recent years, we have witnessed an explosion of successful applications of deep learning, including object extraction, speech recognition, machine translation, car driving, recommendation systems, etc. In many applications of machine learning, such as machine learning for medical diagnosis, we would like to have machine learning algorithms that do not memorize sensitive information about the training set, such as the specific medical histories of individual patients.

Machine learning algorithms work by studying a lot of data and updating their parameters to encode the relationships in that data. Ideally, we would like the parameters of these machine learning models to encode general patterns rather than specific facts about specific training examples. Unfortunately, machine learning algorithms do not learn to ignore these specifics by default. If we want to use machine learning to solve an important task, like making a cancer diagnosis model, then when we publish that machine learning model, we might also inadvertently reveal information about the training set. A malicious attacker might be able to inspect the published model and learn private information.

Scientists have proposed many approaches to provide privacy when analyzing data. For instance, it is popular to anonymize the data before it is analyzed, by removing private details or replacing them with random values. Common examples of details often anonymized include phone numbers and zip codes. However, anonymizing data is not always sufficient and the privacy it provides quickly degrades as adversaries obtain auxiliary information about the individuals represented in the dataset.

Centrally kept data is subject to legal subpoenas and extra-judicial surveillance. Many personal data - for example, medical institutions that may want to apply deep learning methods to clinical records - are prevented, for reasons of privacy and confidentiality, from sharing data and thus benefiting from large-scale deep learning.

The objective of this thesis is to design, implement and evaluate a practical system that allows several parties to jointly learn a specific neural network model for a given purpose without sharing their input data. This is to exploit the fact that the optimization algorithms used in modern deep learning, namely those based on stochastic gradient descent, can be paralleled and executed asynchronously. One of the objectives would be for each participant to train independently on his or her own data set while selectively sharing with other participants a subset of the key parameters of his or her model. Each participant thus preserves the confidentiality of his data while taking advantage of the models of the other participants, which allows him to improve the accuracy of learning beyond what is only possible with his own data.

For example, one could imagine that a network of doctors or hospitals could exchange parts of the model in this way rather than building a single global system hosting all the data.

This project is obviously carried out in collaboration with the medical teams of the University Hospital and in particular with the Department of Medical Informatics (DIM) headed by Professor Pascal STACCINI.

This thesis is part of the IDB project funded by IDEX UCA IDEX. Anonymous data are available representing 10 years of EHRs for care and resuscitation suites (PMSI SSR) and for medicine, surgery and obstetrics (PMSI MCO).

Posición de investigador de tiempo completo en la Universidad de Passau

This is a full-time position initially for one year with the option of renewal.

Your responsibilities

• Collaboration on the H2020 project SEMIOTICS (semiotics-project.eu) funded by the European Commission
• Elaboration of current IT-Security topics: particularly in the following areas:
  • Extension of existing open source projects related to authentication, identity management, and access control (NodeJs, python, among other languages)
  • Monitoring of computational resources, such as processing, storage, and networking in Kubernetes framework, or OpenStack, depending on the project’s decision.
  • Prediction of threats to availability for components developed by the consortium, based on results from monitoring or resources. In this regard, a machine learning background would be highly appreciated. pintas
  • Refine an existing threat analysis on particular use cases to apply security mechanisms, as security functionality becomes available.
  • Implement demonstrations for the security components developed within the project by our University.
  • Although the previous aspects are the focus of the role, the candidate would likely contribute to security-related aspects of Software Defined Networks (SDN).
  • Likewise, the implementation of prediction algorithms in embedded devices with limited memory and processing capacity could be needed.
• Assistance on the conception and elaboration of new research projects on IT-Securit
• Opportunity of doctoral research

Personal requirements

• Excellent university degree (M.Sc. or comparable) in Informatics or related field
• Experience with IT-Security (esp. applied cryptography) and Cloud Computing
• Willingness to cooperate with national and international researchers (incl. traveling)
• Very good English skills, both written and spoken
• Teamwork skills, openness, flexibility and the ability to work independently

What we offer

• Remuneration in accordance with pay grade E13 of the German public-sector collective agreement TV-L, salary level dependent on qualifications and experience
• A rewarding, diverse and challenging academic position on a modern, verdant campus located on the banks of the river Inn, a few minutes' walk from Passau’s historic Old Town
• A great work climate in a family-friendly environment
• Very good English skills, both written and spoken
• The opportunity to contribute to open source solutions on the IT security field.

The University of Passau wishes to increase the proportion of its female staff and expressly encourages women to apply for the position. This position is suitable for candidates with disabilities. Disabled persons will be given preference if the personal aptitudes and qualifications are equal.

If you have any further questions about this position, please contact Dr. Joachim Posegga by e-mail (Esta dirección de correo electrónico está siendo protegida contra los robots de spam. Necesita tener JavaScript habilitado para poder verlo.) or by telephone +49-851-509-3211.

To apply, please send your full application (including school, training and work certificates) in only one file in the pdf format to Esta dirección de correo electrónico está siendo protegida contra los robots de spam. Necesita tener JavaScript habilitado para poder verlo.. Once the application process has been completed, we will retain your application on file for five months before deleting it from our computer systems.