The rise of cloud computing technology led to a paradigm shift in technological services that enabled enterprises to delegate their data analytics tasks to third party (cloud) servers. Machine learning as a service (MLaaS) provides stakeholders with the ease to perform machine learning tasks on a cloud platform.
The advantage of outsourcing these computationally-intensive operations unfortunately comes with high cost in terms of privacy exposures. The goal is therefore to come up with customised machine learning algorithms that would, by design, preserve the privacy of the processed data. Advanced cryptographic techniques, such as fully homomorphic encryption or secure multi-party computation, enable the execution of some operations over encrypted data and therefore can be considered as potential candidates for these algorithms. However, these incur high computational and/or communication costs for some operations.
During this online event, Prof. Melek Önen, associate professor in the Digital Security Department at EURECOM (Sophia-Antipolis, France), will analyse the tension between machine learning techniques and relevant cryptographic tools. Furthermore, she will give an overview existing solutions addressing both privacy and security.
Join the event by following this link: https://unilu.webex.com/unilu/j.php?MTID=ma76ec8727da2e913fd139157cd0e833b (event password: 4M5sTM9iPvW, from phones: 46578694)
Bio:
Melek Önen is an Associate Professor in the Digital Security Department at EURECOM (Sophia-Antipolis, France). Her research interests are applied cryptography, information security and privacy. She has worked in the design and the development of cryptographic protocols for various technologies including Big Data and the IoT. She holds a PhD in Computer Science from Ecole Nationale Supérieure des Télécommunications de Paris (ENST, 2005).
