The increasing size and complexity of datasets have accelerated the development of machine learning models and exposed the need for more scalable solutions. This thesis explores challenges associated with large-scale machine learning under data privacy constraints. With the growth of machine learning models, traditional privacy methods such as data anonymization are becoming insufficient. Thus, we delve into alternative approaches, such as differential privacy. Our research addresses the following core areas in the context of scalable privacy-preserving machine learning: First, we examine the implications of data dimensionality on privacy for the application of medical image analysis. We extend the classification algorithm Private Aggregati...
Privacy-preserving, and more concretely differentially private machine learning, is concerned with ...
As artificial intelligence becomes more and more prevalent, machine learning algorithms are being us...
Data holders are increasingly seeking to protect their user’s privacy, whilst still maximizing their...
The increasing size and complexity of datasets have accelerated the development of machine learning ...
Modern machine learning increasingly involves personal data, such as healthcare, financial and user ...
Using machine learning to improve health care has gained popularity. However, most research in machi...
Neural networks are known to memorize parts of their training set. Therefore, whenever sensitive inf...
Privacy has never been more important to maintain in today’s information society. Companies and orga...
Social Network Sites (SNS) such as Facebook and Twitter, play a great role in our lives. On one hand...
Machine learning applications in fields where data is sensitive, such as healthcare and banking, fac...
The increased generation of data has become one of the main drivers of technological innovation in h...
Social Network Sites (SNS) such as Facebook and Twitter, have been playing a great role in our lives...
International audienceThis work addresses the problem of learning from large collections of data wit...
The past decade has witnessed the fast growth and tremendous success of machine learning. However, r...
Recent years have witnessed a rapid development in machine learning systems and a widespread increas...
Privacy-preserving, and more concretely differentially private machine learning, is concerned with ...
As artificial intelligence becomes more and more prevalent, machine learning algorithms are being us...
Data holders are increasingly seeking to protect their user’s privacy, whilst still maximizing their...
The increasing size and complexity of datasets have accelerated the development of machine learning ...
Modern machine learning increasingly involves personal data, such as healthcare, financial and user ...
Using machine learning to improve health care has gained popularity. However, most research in machi...
Neural networks are known to memorize parts of their training set. Therefore, whenever sensitive inf...
Privacy has never been more important to maintain in today’s information society. Companies and orga...
Social Network Sites (SNS) such as Facebook and Twitter, play a great role in our lives. On one hand...
Machine learning applications in fields where data is sensitive, such as healthcare and banking, fac...
The increased generation of data has become one of the main drivers of technological innovation in h...
Social Network Sites (SNS) such as Facebook and Twitter, have been playing a great role in our lives...
International audienceThis work addresses the problem of learning from large collections of data wit...
The past decade has witnessed the fast growth and tremendous success of machine learning. However, r...
Recent years have witnessed a rapid development in machine learning systems and a widespread increas...
Privacy-preserving, and more concretely differentially private machine learning, is concerned with ...
As artificial intelligence becomes more and more prevalent, machine learning algorithms are being us...
Data holders are increasingly seeking to protect their user’s privacy, whilst still maximizing their...