Interpretable Machine Learning for Privacy-Preserving Pervasive Systems
نویسندگان
چکیده
منابع مشابه
Interpretable Machine Learning for Privacy-Preserving IoT and Pervasive Systems
The presence of pervasive computing in our everyday lives and emergence of the Internet of Things, such as the interaction of users with connected devices like smartphones or home appliances generate increasing amounts of traces that reflect users’ behavior. A plethora of machine learning techniques enable service providers to process these traces to extract latent information about the users. ...
متن کاملPrivacy Preserving Machine Learning: Related Work
A practical scenario of PPML is where only one central party has the entire data on which the ML algorithm has to be learned. Agrawal and Ramakrishnan [1] proposed the first method to learn a Decision Tree classifier on a database without revealing any information about individual records. They consider public model private data setting where the algorithm and its parameters are public whereas ...
متن کاملPrivacy Preserving for Efficient Authentication in Pervasive
In the present computer era and advancement in mobile communication system where many applications rely on the existence of small devices and small applications which exchange data in any communication networks challenging is to provide security where the significant portion of applications is based on the confidentiality and integrity of messages that are communicated by short encrypted messag...
متن کاملPrivacy-Preserving Triggers for Pervasive Spaces
Providing pervasive services often necessitates gathering information about individuals that may be considered sensitive. Often, one is forced to make a difficult choice: either to risk loss of privacy or to let go of the benefits pervasive technology offers. Our conjecture is that such a choice is not always necessary. It is possible to design data collection strategies in such a way that serv...
متن کاملMaking machine learning models interpretable
Data of different levels of complexity and of ever growing diversity of characteristics are the raw materials that machine learning practitioners try to model using their wide palette of methods and tools. The obtained models are meant to be a synthetic representation of the available, observed data that captures some of their intrinsic regularities or patterns. Therefore, the use of machine le...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Pervasive Computing
سال: 2020
ISSN: 1536-1268,1558-2590
DOI: 10.1109/mprv.2019.2918540