Quantization is commonly used to compress and accelerate deep neural
net...
We construct a strong PUF with provable security against ML attacks on b...
DNNs deployed on analog processing in memory (PIM) architectures are sub...
With proliferation of DNN-based applications, the confidentiality of DNN...
Modern recommendation systems rely on real-valued embeddings of categori...
We propose a strong physical unclonable function (PUF) that is provably
...