Search
Now showing items 1501-1510 of 1526
Secure inference of quantized neural networks
(Massachusetts Institute of Technology, 2020)
Running image recognition algorithms on medical datasets raises several privacy concerns. Hospitals may not have access to an image recognition model that a third party may have developed, and medical images are HIPAA ...
Senti : a wearable sensor for physiological data acquisition in early education
(Massachusetts Institute of Technology, 2016)
Wearable sensors have been used in research efforts aiming to develop a mapping between physiological responses of the autonomic nervous system, namely electrodermal activity and heart rate variability, to emotional reactions ...
Evaluating modern defenses against control flow hijacking
(Massachusetts Institute of Technology, 2015)
Memory corruption attacks continue to be a major vector of attack for compromising modern systems. Strong defenses such as complete memory safety for legacy languages (C/C++) incur a large overhead, while weaker and practical ...
Design and implementation of search for the Scratch Online Community
(Massachusetts Institute of Technology, 2016)
The Scratch Online Community has been experiencing rapid growth and has around 9.5 million users and 12.5 million shared projects today. This exponential growth introduces a need for a new Search infrastructure that will ...
A distributed metadata-private messaging system
(Massachusetts Institute of Technology, 2016)
Private communication over the Internet continues to be a difficult problem. Even if messages are encrypted, it is hard to deliver them without revealing metadata about which pairs of users are communicating. Scalable ...
Representation learning for non-sequential data
(Massachusetts Institute of Technology, 2018)
In this thesis, we design and implement new models to learn representations for sets and graphs. Typically, data collections in machine learning problems are structured as arrays or sequences, with sequential relationships ...
Towards building active defense for software applications
(Massachusetts Institute of Technology, 2018)
Over the last few years, cyber attacks have become increasingly sophisticated. In an effort to defend themselves, corporations often look to machine learning, aiming to use the large amount of data collected on cyber attacks ...
Invariance properties of the human visual system in one-shot learning
(Massachusetts Institute of Technology, 2017)
This work first characterizes human invariant recognition in one-shot learning. By using novel stimuli, we address the question whether invariance to transformation emerges from experience and memorization of templates or ...
TaleBlazer : indoor positioning
(Massachusetts Institute of Technology, 2016)
TaleBlazer is a platform that allows for the design and play of iOS and Android location-based augmented reality games. Until recently, TaleBlazer games could only be played outdoors. Indoor positioning is an active area ...
Design of on-chip monitoring circuits for clock delay and temperature
(Massachusetts Institute of Technology, 2016)
As devices continue to scale, Process, Voltage and Temperature (PVT) variations tend to have a bigger impact on circuit performance. The ability to measure this impact provides essential knowledge about the circuit's current ...