S
Srinivas Devadas
Researcher at Massachusetts Institute of Technology
Publications - 498
Citations - 35003
Srinivas Devadas is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Sequential logic & Combinational logic. The author has an hindex of 88, co-authored 480 publications receiving 31897 citations. Previous affiliations of Srinivas Devadas include University of California, Berkeley & Cornell University.
Papers
More filters
Patent
Private data processing
TL;DR: In this paper, a method for processing one or more terms includes, at a first computation facility, computing an obfuscated numerical representation for each of the terms, provided from the first facility to a second computation facility.
Proceedings ArticleDOI
Robomorphic computing: a design methodology for domain-specific accelerators parameterized by robot morphology
Sabrina M. Neuman,Brian Plancher,Thomas Bourgeat,Thierry Tambe,Srinivas Devadas,Vijay Janapa Reddi +5 more
TL;DR: In this article, a methodology to transform robot morphology into a customized hardware accelerator morphology is presented, using robot topology and structure to exploit parallelism and matrix sparsity patterns in accelerator hardware.
Proceedings ArticleDOI
GENIE: A Generalized Array Optimizer for VLSI Synthesis
Srinivas Devadas,A.R. Newton +1 more
TL;DR: A new generalized array optimization scheme is presented which solves the problem of efficient automatic layout of multi-level CMOS and NMOS logic circuits and is implemented in the program GENIE, the first program to produce high-quality, automated SLA implementations.
Proceedings ArticleDOI
Verification of interacting sequential circuits
TL;DR: Pipeline latches are easily incorporated into the generalized, hierarchical verification strategy whereby the states of pipeline latches can be implicitly enumerated, and Experimental results indicate the superior efficiency of this approach as compared to previous approaches for FSM verification.
Journal ArticleDOI
Var-CNN: A Data-Efficient Website Fingerprinting Attack Based on Deep Learning
TL;DR: Var-CNN as discussed by the authors leverages deep learning techniques along with novel insights specific to packet sequence classification to improve the performance of website fingerprinting attacks, achieving a higher true positive rate (TPR) than state-of-the-art attacks.