Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Neural Network-based Inherently Fault-tolerant Hardware Cryptographic Primitives without Explicit Redundancy Checks

Neural Network-based Inherently Fault-tolerant Hardware Cryptographic Primitives without Explicit... Fault injection-based cryptanalysis is one of the most powerful practical threats to modern cryptographic primitives. Popular countermeasures to such fault-based attacks generally use some form of redundant computation to detect and react/correct the injected faults. However, such countermeasures are shown to be vulnerable to selective fault injections. In this article, we aim to develop a cryptographic primitive that is fault tolerant by its construction and does not require to compute the same value multiple times. We utilize the effectiveness of Neural Networks (NNs), which show “some degree” of robustness by functioning correctly even after the occurrence of faults in any of its parameters. We also propose a novel strategy that enhances the fault tolerance of the implementation to “high degree” (close to 100%) by incorporating selective constraints in the NN parameters during the training phase. We evaluated the performance of revised NN considering both software and FPGA implementations for standard cryptographic primitives like 88 AES SBox and 44 PRESENT SBox. The results show that the fault tolerance of such implementations can be significantly increased with the proposed methodology. Such NN-based cryptographic primitives will provide inherent resistance against fault injections without requiring any redundancy countermeasures. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Journal on Emerging Technologies in Computing Systems (JETC) Association for Computing Machinery

Neural Network-based Inherently Fault-tolerant Hardware Cryptographic Primitives without Explicit Redundancy Checks

Download PDF
30 pages

Loading next page...
 
/lp/association-for-computing-machinery/neural-network-based-inherently-fault-tolerant-hardware-cryptographic-UMJzEQpX06

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
Association for Computing Machinery
Copyright
Copyright © 2020 ACM
ISSN
1550-4832
eISSN
1550-4840
DOI
10.1145/3409594
Publisher site
See Article on Publisher Site

Abstract

Fault injection-based cryptanalysis is one of the most powerful practical threats to modern cryptographic primitives. Popular countermeasures to such fault-based attacks generally use some form of redundant computation to detect and react/correct the injected faults. However, such countermeasures are shown to be vulnerable to selective fault injections. In this article, we aim to develop a cryptographic primitive that is fault tolerant by its construction and does not require to compute the same value multiple times. We utilize the effectiveness of Neural Networks (NNs), which show “some degree” of robustness by functioning correctly even after the occurrence of faults in any of its parameters. We also propose a novel strategy that enhances the fault tolerance of the implementation to “high degree” (close to 100%) by incorporating selective constraints in the NN parameters during the training phase. We evaluated the performance of revised NN considering both software and FPGA implementations for standard cryptographic primitives like 88 AES SBox and 44 PRESENT SBox. The results show that the fault tolerance of such implementations can be significantly increased with the proposed methodology. Such NN-based cryptographic primitives will provide inherent resistance against fault injections without requiring any redundancy countermeasures.

Journal

ACM Journal on Emerging Technologies in Computing Systems (JETC) – Association for Computing Machinery

Published: Sep 22, 2020

Keywords: FPGA implementation

References

  • An improved differential fault analysis on AES-256
    Ali, Subidh; Mukhopadhyay, Debdeep
  • A parity code based fault detection for an implementation of the advanced encryption standard
    Bertoni, Guido; Breveglieri, Luca; Koren, Israel; Maistri, Paolo; Piuri, Vincenzo
  • Error analysis and detection procedures for a hardware implementation of the advanced encryption standard
    Bertoni, Guido; Breveglieri, Luca; Koren, Israel; Maistri, Paolo; Piuri, Vincenzo
  • PRESENT: An ultra-lightweight block cipher
    Bogdanov, Andrey; Knudsen, Lars R.; Leander, Gregor; Paar, Christof; Poschmann, Axel; Robshaw, Matthew J. B.; Seurin, Yannick; Vikkelsoe, C.
  • Keras
    et al, François Chollet
  • Exploiting correcting codes: On the effectiveness of ECC memory against rowhammer attacks
    Cojocar, Lucian; Razavi, Kaveh; Giuffrida, Cristiano; Bos, Herbert
  • The Design of Rijndael: AES—The Advanced Encryption Standard
    Daemen, Joan; Rijmen, Vincent
  • M8M: Masks and macs against physical attacks
    De Meyer, Lauren; Arribas, Victor; Nikova, Svetla; Nikov, Ventzislav; Rijmen, Vincent
  • Analyzing and increasing the reliability of convolutional neural networks on GPUs
    Santos, Fernando Fernandes dos; Pimenta, Pedro Foletto; Lunardi, Caio B.; Draghetti, Lucas; Carro, Luigi; Kaeli, David R.; Rech, Paolo
  • A framework for evaluation and analysis on infection countermeasures against fault attacks
    Feng, Jingyi; Chen, Hua; Li, Yang; Jiao, Zhipeng; Xi, Wei
  • Preventing fault attacks using fault randomization with a case study on AES
    Ghosh, Shamit; Saha, Dhiman; Sengupta, Abhrajit; Chowdhury, Dipanwita Roy
  • Infective computation and dummy rounds: Fault protection for block ciphers without check-before-output
    Gierlichs, Benedikt; Schmidt, Jörn-Marc; Tunstall, Michael
  • Recomputing with permuted operands: A concurrent error detection approach
    Guo, Xiaofei; Karri, Ramesh
  • Experimental evaluation of deep neural network resistance against fault injection attacks
    Hou, Xiaolu; Breier, Jakub; Jap, Dirmanto; Ma, Lei; Bhasin, Shivam; Liu, Yang
  • Parity-based concurrent error detection of substitution-permutation network block ciphers
    Karri, Ramesh; Kuznetsov, Grigori; Gössel, Michael
  • Concurrent structure-independent fault detection schemes for the advanced encryption standard
    Kermani, Mehran Mozaffari; Reyhani-Masoleh, Arash
  • On application of neural networks for s-boxes design
    Kotlarz, Piotr; Kotulski, Zbigniew
  • Fault injection attack on deep neural network
    Liu, Yannan; Wei, Lingxiao; Luo, Bo; Xu, Qiang
  • Double-data-rate computation as a countermeasure against fault analysis
    Maistri, Paolo; Leveugle, Régis
  • A comparative cost/security analysis of fault attack countermeasures
    Malkin, Tal; Standaert, François-Xavier; Yung, Moti
  • Fault tolerance of the backpropagation neural network trained on noisy inputs
    Minnix, J. I.
  • Synaptic weight noise during multilayer perceptron training: Fault tolerance and training improvements
    Murray, Alan F.; Edwards, Peter J.
  • Enhanced MLP performance and fault tolerance resulting from synaptic weight noise during training
    Murray, Alan F.; Edwards, Peter J.
  • Maximally fault tolerant neural networks
    Neti, Chalapathy; Schneider, Michael H.; Young, Eric D.
  • Threshold implementations against side-channel attacks and glitches
    Nikova, Svetla; Rechberger, Christian; Rijmen, Vincent
  • A biased fault attack on the time redundancy countermeasure for AES
    Patranabis, Sikhar; Chakraborty, Abhishek; Nguyen, Phuong Ha; Mukhopadhyay, Debdeep
  • Complete and partial fault tolerance of feedforward neural nets
    Phatak, Dhananjay S.; Koren, Israel
  • A differential fault attack technique against SPN structures, with application to the AES and KHAZAD
    Piret, Gilles; Quisquater, Jean-Jacques
  • Performance and fault-tolerance of neural networks for optimization
    Protzel, Peter W.; Palumbo, Daniel L.; Arras, Michael K.
  • Reliable Software for Unreliable Hardware—A Cross Layer Perspective
    Rehman, Semeen; Shafique, Muhammad; Henkel, Jörg
  • Fault tolerance of pruned multilayer networks
    Segee, B. E.; Carter, M. J.
  • Attack on a DFA protected AES by simultaneous laser fault injections
    Selmke, Bodo; Heyszl, Johann; Sigl, Georg
  • Investigating the fault tolerance of neural networks
    Tchernev, Elko B.; Mulvaney, Rory G.; Phatak, Dhananjay S.
  • Perfect fault tolerance of the n-k-n network
    Tchernev, Elko B.; Mulvaney, Rory G.; Phatak, Dhananjay S.
  • Exploration of benes network in cryptographic processors: A random infection countermeasure for block ciphers against fault attacks
    Wang, Bo; Liu, Leibo; Deng, Chenchen; Zhu, Min; Yin, Shouyi; Zhou, Zhuoquan; Wei, Shaojun
  • Differential fault analysis on PRESENT key schedule
    Wang, Gaoli; Wang, Shaohui
  • A method for designing S-box based on chaotic neural network
    Wang, Yong; Yang, Li; Li, Min; Song, Sihong
  • Low cost concurrent error detection for the advanced encryption standard
    Wu, Kaijie; Karri, Ramesh; Kuznetsov, Grigori; Gössel, Michael