Cryptosystem designers frequently assume that secrets will be manipulated in closed, reliable computing environments. Unfortunately, actual computers and microchips leak information about the operations they process. This paper examines specific methods for analyzing power consumption measurements to find secret keys from tamper resistant devices. We also discuss approaches for building cryptosystems that can operate securely in existing hardware that leaks information.

/pdf/differential-power-analysis-4t7fjmuc7b.pdf

Differential Power Analysis

This monograph provides an overview of general deep learning methodology and its applications to a variety of signal and information processing tasks. The application areas are chosen with the following three criteria in mind: (1) expertise or knowledge of the authors; (2) the application areas that have already been transformed by the successful use of deep learning technology, such as speech recognition and computer vision; and (3) the application areas that have the potential to be impacted significantly by deep learning and that have been experiencing research growth, including natural language and text processing, information retrieval, and multimodal information processing empowered by multi-task deep learning.

/pdf/deep-learning-methods-and-applications-5cyi610sjz.pdf

Deep Learning: Methods and Applications

This ebook is the first authorized digital version of Kernighan and Ritchie's 1988 classic, The C Programming Language (2nd Ed.). One of the best-selling programming books published in the last fifty years, "K&R" has been called everything from the "bible" to "a landmark in computer science" and it has influenced generations of programmers. Available now for all leading ebook platforms, this concise and beautifully written text is a "must-have" reference for every serious programmers digital library.

As modestly described by the authors in the Preface to the First Edition, this "is not an introductory programming manual; it assumes some familiarity with basic programming concepts like variables, assignment statements, loops, and functions. Nonetheless, a novice programmer should be able to read along and pick up the language, although access to a more knowledgeable colleague will help."

The C programming language

Recently, the hybrid deep neural network (DNN)- hidden Markov model (HMM) has been shown to significantly improve speech recognition performance over the conventional Gaussian mixture model (GMM)-HMM. The performance improvement is partially attributed to the ability of the DNN to model complex correlations in speech features. In this paper, we show that further error rate reduction can be obtained by using convolutional neural networks (CNNs). We first present a concise description of the basic CNN and explain how it can be used for speech recognition. We further propose a limited-weight-sharing scheme that can better model speech features. The special structure such as local connectivity, weight sharing, and pooling in CNNs exhibits some degree of invariance to small shifts of speech features along the frequency axis, which is important to deal with speaker and environment variations. Experimental results show that CNNs reduce the error rate by 6%-10% compared with DNNs on the TIMIT phone recognition and the voice search large vocabulary speech recognition tasks.

/pdf/convolutional-neural-networks-for-speech-recognition-59lskxzlgf.pdf

Convolutional neural networks for speech recognition

From the Publisher:
Connectionist Speech Recognition: A Hybrid Approach describes the theory and implementation of a method to incorporate neural network approaches into state-of-the-art continuous speech recognition systems based on Hidden Markov Models (HMMs) to improve their performance. In this framework, neural networks (and in particular, multilayer perceptrons or MLPs) have been restricted to well-defined subtasks of the whole system, i.e., HMM emission probability estimation and feature extraction. The book describes a successful five year international collaboration between the authors. The lessons learned form a case study that demonstrates how hybrid systems can be developed to combine neural networks with more traditional statistical approaches. The book illustrates both the advantages and limitations of neural networks in the framework of a statistical system. Using standard databases and comparing with some conventional approaches, it is shown that MLP probability estimation can improve recognition performance. Other approaches are discussed, though there is no such unequivocal experimental result for these methods. Connectionist Speech Recognition: A Hybrid Approach is of use to anyone intending to use neural networks for speech recognition or within the framework provided by an existing successful statistical approach. This includes research and development groups working in the field of speech recognition, both with standard and neural network approaches, as well as other pattern recognition and/or neural network researchers. This book is also suitable as a text for advanced courses on neural networks or speech processing.

Connectionist Speech Recognition: A Hybrid Approach

In this paper, two packing algorithms for the detection of activity profiles in MTCMOS-based FPGA structures are proposed for leakage power mitigation The first algorithm is a connection-based packing technique by which the proximity of the logic blocks is accounted for, and the second algorithm is a logic-based packing approach by which the weighted Hamming distance between the blocks activities is considered After both algorithms are analyzed, they are applied to a number of FGPA benchmarks for verification Once the activity profiles are realized, sleep transistors are carefully positioned to contain the clustered blocks that share similar activity profiles Finally, the percentage of the leakage power savings for each of the two algorithms is evaluated

/pdf/activity-packing-in-fpgas-for-leakage-power-reduction-1hz8a34pn6.pdf

Activity Packing in FPGAs for Leakage Power Reduction

SPAID, a design tool that maps digital signal processing (DSP) algorithms into a multibus VLSI architecture is discussed. Algorithm structure, design style of functional units (FU), and parallelism of the architecture are all explored in the design space. SPAID supports pipelined and multicycle functional units. The synthesized processor is a self-timed element externally, while it is internally synchronous. SPAID explores a wider space, and produces better solutions compared with existing synthesis systems on an elliptic filter benchmark design example. A multibus multifunctional unit processor matched to the implemented algorithm is synthesized using SPAID. >

SPAID: an architectural synthesis tool for DSP custom applications

Inspired by the huge improvement in the RF properties of CMOS, RF designers are invading the wireless market with all-CMOS RF transceivers and system-on-chip implementations. In this work, the impact of technology scaling on the RF properties of the CMOS; frequency properties, noise performance, linearity, stability, and non-quasi static effects, is investigated to provide RF designers with an insight to the capabilities of future CMOS technologies. Using the BSIM4 model it is found that future CMOS technologies have high prospects in the RF industry.

Impact of technology scaling on RF CMOS

A new high-speed Domino circuit, called HS-Domino has been developed. HS-Domino resolves the tradeoff between performance and reliability in conventional CD-Domino logic while dissipating low dynamic power with minimal area over- head. HS-Domino, therefore, extends Domino's operation in the deep submicron regime. A multithreshold implementation of HS-Domino is also devised to achieve substantially low leakage values during standby, while maintaining high performance and low power during the active mode. Furthermore, the generic multithreshold scheme is applied to differential cascode voltage switch (DDCVS) logic.

http://ieeexplore.ieee.org/iel5/92/21460/00994977.pdf

Energy-Efficient Noise-Tolerant Dynamic Styles for

Multi-threshold MOS current mode logic (MTMCML) is a natural evolution for MCML that offers power saving through supply voltage reduction while retaining the same performance. In this work, analytical formulation based on the BSIM3v3 model is proposed for MTMCML with error within 10% compared to HSPICE. The formulation helps designers to efficiently design MTMCML circuits without undergoing the time-consuming HSPICE simulations. Furthermore, it provides design guidelines and aids for designers to fully understand the different tradeoffs in MTMCML design. In addition, the analysis is extended to study the impact of technology scaling and parameter variations on MTMCML. It is shown that the worst case variation in the minimum supply voltage of MTMCML is 1.16%, thus suggesting maximal power saving.

Mohamed I. Elmasry

Papers

Activity Packing in FPGAs for Leakage Power Reduction

SPAID: an architectural synthesis tool for DSP custom applications

Impact of technology scaling on RF CMOS

Energy-Efficient Noise-Tolerant Dynamic Styles for

Analysis and design of low-power multi-threshold MCML