Energy-Aware, Secure and Reliable Computing
We are part of the Electrical and Computer Engineering Department at New York University. Our research is at the intersections of computer hardware design, cyber-security, and machine learning with a focus on building energy-efficient (En), secure (Su), and reliable (Re) computing systems. We are always looking for talented students to join our group. If you are interested please e-mail Prof. Siddharth Garg.
The EnSuRe Lab is part of NYU Center for Cybersecurity and NYU WIRELESS. For more details, see the video above or our Projects and Publications pages.
Our paper on stochastic ReLU functions for private inference will appear at Neural Information Processing Systems (NeuRIPS) 2021! The work is led by EnSuRe alum Zahra Ghodsi, and in collaboration with Brandon Reagen and Nandan Jha. The latency of many cryptographic private inference schemes is dominated by ReLUs. Circa introduces a new stochastic ReLU function […]
Our work on Single-Shot Compression for Hypothesis Testing received two awards! – Best Student Paper Award (2nd place) at IEEE SPAWC 2021– Best Poster Award (1st place) at IEEE CTW 2021Fabrizio also presented a poster on the same work at ITR3 @ ICML 2021 and IEEE NASIT 2021. Reference:F. Carpi, S. Garg, E. Erkip, “Single-Shot Compression for Hypothesis Testing,” in Proc. […]
Joint work with Nandan Jha, Zahra Ghodsi and Brandon Reagen, DeepReDuce seeks to eliminate redundant or ineffectual ReLUs from a deep network to support private inference. Compared to the state-of-the-art for private inference, DeepReDuce improves accuracy and reduced ReLU count by up to 3.5% and 3.5×, respectively.
