s3gfault

urv | 2023.08.22

exploring how to maintain privacy at untrusted edges as part of CICS's undergraduate volunteer research program (URV)

Enabling Trust in ML Models on Untrusted Edges

Worked alongside PhD mentor in Winter 2022-2023. Proposed a long short-term split (LSTM-SPLIT) machine learning model to help obfuscate private data sent between client-server models on untrustworthy edge nodes.

Using Your Head: Identifying Windows Malware by Deep Learning on PE Headers

An analysis into utilizing deep learning NN models like multi-layer perceptrons and fully-connected nets to learn if certain features in Windows PE header files are indicative of malware or not.