-
Chapter and Conference Paper
EdgeMixup: Embarrassingly Simple Data Alteration to Improve Lyme Disease Lesion Segmentation and Diagnosis Fairness
Lyme disease is a severe skin disease caused by tick bites, which affects hundreds of thousands of people. One task in diagnosing Lyme disease is lesion segmentation, i.e., separating benign skin from lesions,...
-
Chapter and Conference Paper
Addressing Heterogeneity in Federated Learning via Distributional Transformation
Federated learning (FL) allows multiple clients to collaboratively train a deep learning model. One major challenge of FL is when data distribution is heterogeneous, i.e., differs from one client to another. E...
-
Chapter and Conference Paper
Defending Medical Image Diagnostics Against Privacy Attacks Using Generative Methods: Application to Retinal Diagnostics
Machine learning (ML) models used in medical imaging diagnostics can be vulnerable to a variety of privacy attacks, including membership inference attacks, that lead to violations of regulations governing the use...
-
Chapter and Conference Paper
PatchAttack: A Black-Box Texture-Based Attack with Reinforcement Learning
Patch-based attacks introduce a perceptible but localized change to the input that induces misclassification. A limitation of current patch-based black-box attacks is that they perform poorly for targeted atta...
-
Chapter and Conference Paper
Abusing Browser Address Bar for Fun and Profit - An Empirical Investigation of Add-On Cross Site Scripting Attacks
Add-on JavaScript originating from users’ inputs to the browser brings new functionalities such as debugging and entertainment, however it also leads to a new type of cross-site scripting attack (defined as ad...
-
Chapter and Conference Paper
Uranine: Real-time Privacy Leakage Monitoring without System Modification for Android
Mobile devices are becoming increasingly popular. One reason for their popularity is the availability of a wide range of third-party applications, which enrich the environment and increase usability. There are...
-
Chapter and Conference Paper
Protecting Web-Based Single Sign-on Protocols against Relying Party Impersonation Attacks through a Dedicated Bi-directional Authenticated Secure Channel
Web-based single sign-on describes a class of protocols where a user signs into a web site with the authentication provided as a service by a third party. In exchange for the increased complexity of the authen...
