X-Fault: Impact of Faults on Binary Neural Networks in Memristor-Crossbar Arrays with Logic-in-Memory Computation

Staudigl, Felix; Sturm, Karl J. X.; Maximilian, Bartel,; Fetz, Thorben; Šišejković, Dominik; Joseph, Jan Moritz; Pohls, Leticia Bolzani; Leupers, Rainer

doi:10.1109/aicas54282.2022.9869897

Cited by 5 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Availability, confidentiality, and integrity are the three cornerstones of hardware security that must be considered during the design process. While most research focuses on the integrity property [4], [5],…”

Section: Introductionmentioning

confidence: 99%

Quantitative Information Flow for Hardware: Advancing the Attack Landscape

Reimann

Erdönmez

Šišejković

et al. 2023

2023 IEEE 14th Latin America Symposium on Circuits and Systems (LASCAS)

View full text Add to dashboard Cite

Novel non-volatile memory (NVM) technologies offer high-speed and high-density data storage. In addition, they overcome the von Neumann bottleneck by enabling computingin-memory (CIM). Various computer architectures have been proposed to integrate CIM blocks in their design, forming a mixed-signal system to combine the computational benefits of CIM with the robustness of conventional CMOS. Novel electronic design automation (EDA) tools are necessary to design and manufacture these so-called neuromorphic systems. Furthermore, EDA tools must consider the impact of security vulnerabilities, as hardware security attacks have increased in recent years. Existing information flow analysis (IFA) frameworks offer an automated tool-suite to uphold the confidentiality property for sensitive data during the design of hardware. However, currently available mixed-signal EDA tools are not capable of analyzing the information flow of neuromorphic systems. To illustrate the shortcomings, we develop information flow protocols for NVMs that can be easily integrated in the already existing tool-suites. We show the limitation of the state-of-the-art by analyzing the flow from sensitive signals through multiple memristive crossbar structures to potential untrusted components and outputs. Finally, we provide a thorough discussion of the merits and flaws of the mixed-signal IFA frameworks on neuromorphic systems.

show abstract

Section: Introductionmentioning

confidence: 99%

Quantitative Information Flow for Hardware: Advancing the Attack Landscape

Reimann

Erdönmez

Šišejković

et al. 2023

2023 IEEE 14th Latin America Symposium on Circuits and Systems (LASCAS)

View full text Add to dashboard Cite

show abstract

A Systematic Literature Review on Binary Neural Networks

et al. 2023

View full text Add to dashboard Cite

This paper presents an extensive literature review on Binary Neural Network (BNN). BNN utilizes binary weights and activation function parameters to substitute the full-precision values. In digital implementations, BNN replaces the complex calculations of Convolutional Neural Networks (CNNs) with simple bitwise operations. BNN optimizes large computation and memory storage requirements, which leads to less area and power consumption compared to full-precision models. Although there are many advantages of BNN, the binarization process has a significant impact on the performance and accuracy of the generated models. To reflect the state-of-the-art in BNN and explore how to develop and improve BNNbased models, we conduct a systematic literature review on BNN with data extracted from 239 research studies. Our review discusses various BNN architectures and the optimization approaches developed to improve their performance. There are three main research directions in BNN: accuracy optimization, compression optimization, and acceleration optimization. The accuracy optimization approaches include quantization error reduction, special regularization, gradient error minimization, and network structure. The compression optimization approaches combine fractional BNN and pruning. The acceleration optimization approaches comprise computing in-memory, FPGA-based implementations, and ASIC-based implementations. At the end of our review, we present a comprehensive analysis of BNN applications and their evaluation metrics. Also, we shed some light on the most common BNN challenges and the future research trends of BNN.

show abstract