We introduce a form of steganography in the domain of machine learning which we call training set camouflage. Imagine Alice has a training set on an illicit machine learning classification task. Alice wants Bob (a machine learning system) to learn the task. However, sending either the training set or the trained model to Bob can raise suspicion if the communication is monitored. Training set camouflage allows Alice to compute a second training set on a completely different – and seemingly benign – classification task.
MadHacks at UW-Madison is hosting a 24-hour hackathon on Nov.10-11th, 2018.
MadHacks’s mission this year is to bring those who are historically under-represented in tech to hackathons. Whether you are a beginner or an expert, MadHacks is the event where you can build the one idea that you always wanted to build with groups of like-minded students.
Mixed effects models are used routinely in the biological and social sciences to share information across groups and to account for data dependence. The statistical properties of such models are often quite good on average across groups, but may be poor for any specific group. For example, commonly-used confidence interval procedures may maintain a target coverage rate on average across groups, but have near zero coverage rate for a group that differs substantially from the others.
Today, we are collecting an immense amount of health data both inside and outside of the hospital. While clinicians are studying ever more data about their patients, they are still ignoring the vast majority of it. Transforming these observational data into actionable knowledge is challenging due to a number of reasons including the presence of confounders, missing context, and complex longitudinal relationships. At the same time, due to the high-stakes nature of healthcare, the field requires tools that are not only accurate, but also interpretable and robust.
Despite the impressive past and recent advances in medical sciences, there are still a host of chronic conditions which are not well understood and lack even consensus description of their signs and symptoms. Without such consensus, research for precise treatments and ultimately a cure is at a halt. Phenotyping these conditions, that is, systematically characterizing the signs, symptoms and other aspects of these conditions, is thus particularly needed.
Commodity operating system kernels are the foundation of our software systems, providing access control, I/O mechanisms, and memory management. However, operating system kernels are vulnerable to a variety of security attacks. Compromising the kernel allows an attacker to render any security protections, provided by the kernel or the applications running on the kernel, useless. Additionally, control of the kernel can be used to launch powerful side-channel attacks against protection systems like Intel SGX.