Fault intensity map analysis with neural network key distinguisher

Physical cryptographic implementations are vulnerable to side-channel attacks, including fault attacks, which can be used to recover a secret key. Using a deep neural network (NN) with fault intensity map analysis (FIMA), we present a new highly efficient statistical fault injection analysis (FIA) technique called FIMA-NN. This technique employs a convolutional neural network to rank the key candidates based on multiple features in data distribution under fault with varying intensities and generalizes most existing statistical techniques including fault sensitivity analysis, differential fault intensity analysis, statistical ineffective fault analysis, and FIMA. As FIMA-NN does not rely on a single feature of data distribution, it is successful even in the presence of a wide variety of countermeasures against FIA. We introduce a generic statistical model for timing failure attacks using dynamic timing analysis of an AES S-box implemented in TSMC 65 nm technology with standard ASIC design flow. Using the simulated fault mechanism, we demonstrate that, in terms of required amount of collected ciphertexts, FIMA-NN is 12.6 times more efficient than statistical techniques using bias alone, when faulty and fault-free values are not filtered. Further, in the presence of error detection and infective countermeasures, FIMA-NN is 4.8 and 5 times more efficient than bias-alone techniques, respectively.

[1]  Christof Paar,et al.  Large laser spots and fault sensitivity analysis , 2016, 2016 IEEE International Symposium on Hardware Oriented Security and Trust (HOST).

[2]  Risi Kondor,et al.  On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups , 2018, ICML.

[3]  Xing Zhang,et al.  A hybrid fault model for differential fault attack on AES , 2017, 2017 IEEE 12th International Conference on ASIC (ASICON).

[4]  Florian Mendel,et al.  Exploiting Ineffective Fault Inductions on Symmetric Cryptography , 2018, IACR Cryptol. ePrint Arch..

[5]  Nahid Farhady Ghalaty,et al.  Differential Fault Intensity Analysis , 2014, 2014 Workshop on Fault Diagnosis and Tolerance in Cryptography.

[6]  Zheng Guo,et al.  Ciphertext-Only Fault Analysis on the LED Lightweight Cryptosystem in the Internet of Things , 2019, IEEE Transactions on Dependable and Secure Computing.

[7]  Dawu Gu,et al.  Impossible Differential Fault Analysis on the LED Lightweight Cryptosystem in the Vehicular Ad-Hoc Networks , 2016, IEEE Transactions on Dependable and Secure Computing.

[8]  P. F. Vasconcelos,et al.  In situ immune response and mechanisms of cell damage in central nervous system of fatal cases microcephaly by Zika virus , 2018, Scientific Reports.

[9]  Claudia Eckert,et al.  Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executables , 2018, 2018 26th European Signal Processing Conference (EUSIPCO).

[10]  Jean-Max Dutertre,et al.  A DFA on AES Based on the Entropy of Error Distributions , 2012, 2012 Workshop on Fault Diagnosis and Tolerance in Cryptography.

[11]  Saibal Mukhopadhyay,et al.  Mitigating Power Supply Glitch based Fault Attacks with Fast All-Digital Clock Modulation Circuit , 2019, 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[12]  Reza Azarderakhsh,et al.  Reliable Inversion in GF(28) With Redundant Arithmetic for Secure Error Detection of Cryptographic Architectures , 2018, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[13]  Nahid Farhady Ghalaty,et al.  Software Fault Resistance is Futile: Effective Single-Glitch Attacks , 2016, 2016 Workshop on Fault Diagnosis and Tolerance in Cryptography (FDTC).

[14]  Bruno Barras,et al.  Using linear codes as a fault countermeasure for nonlinear operations: application to AES and formal verification , 2017, Journal of Cryptographic Engineering.

[15]  Tim Güneysu,et al.  ParTI - Towards Combined Hardware Countermeasures Against Side-Channel and Fault-Injection Attacks , 2016, CRYPTO.

[16]  Debdeep Mukhopadhyay,et al.  Differential Fault Analysis of the Advanced Encryption Standard Using a Single Fault , 2011, WISTP.

[17]  Giorgio Turchetti,et al.  Numerical Convergence of the Block-Maxima Approach to the Generalized Extreme Value Distribution , 2011, 1103.0889.

[18]  Alessandro Barenghi,et al.  A fault induction technique based on voltage underfeeding with application to attacks against AES and RSA , 2013, J. Syst. Softw..

[19]  Frederic P. Miller,et al.  Advanced Encryption Standard , 2009 .

[20]  Philippe Maurine,et al.  Electromagnetic fault injection: the curse of flip-flops , 2016, Journal of Cryptographic Engineering.

[21]  Peter Harremoës,et al.  Rényi Divergence and Kullback-Leibler Divergence , 2012, IEEE Transactions on Information Theory.

[22]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[23]  M. Nirmala Devi,et al.  Hardware Trojan Detection Using Deep Learning Technique , 2019, Advances in Intelligent Systems and Computing.

[24]  Paul Ampadu,et al.  RS-Mask: Random Space Masking as an Integrated Countermeasure against Power and Fault Analysis , 2019, 2020 IEEE International Symposium on Hardware Oriented Security and Trust (HOST).

[25]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Chong Hee Kim,et al.  Differential Fault Analysis against AES-192 and AES-256 with Minimal Faults , 2010, 2010 Workshop on Fault Diagnosis and Tolerance in Cryptography.

[27]  Florian Mendel,et al.  Statistical Ineffective Fault Attacks on Masked AES with Fault Countermeasures , 2018, IACR Cryptol. ePrint Arch..

[28]  Je-Won Kang,et al.  Intrusion Detection System Using Deep Neural Network for In-Vehicle Network Security , 2016, PloS one.

[29]  Joon Beom Seo,et al.  A Perlin Noise-Based Augmentation Strategy for Deep Learning with Small Data Samples of HRCT Images , 2018, Scientific Reports.

[30]  Yang Li,et al.  Fault Sensitivity Analysis , 2010, CHES.

[31]  David Naccache,et al.  When Clocks Fail: On Critical Paths and Clock Faults , 2010, CARDIS.

[32]  Jean-Jacques Quisquater,et al.  A Differential Fault Attack Technique against SPN Structures, with Application to the AES and KHAZAD , 2003, CHES.

[33]  Jinho Bae,et al.  Disposable all-printed electronic biosensor for instantaneous detection and classification of pathogens , 2018, Scientific Reports.

[34]  Paul Ampadu,et al.  FIMA: Fault Intensity Map Analysis , 2019, COSADE.

[35]  Jinoh Kim,et al.  A survey of deep learning-based network anomaly detection , 2017, Cluster Computing.

[36]  Paul Ampadu,et al.  SCAUL: Power Side-Channel Analysis With Unsupervised Learning , 2020, IEEE Transactions on Computers.

[37]  Debdeep Mukhopadhyay,et al.  A Biased Fault Attack on the Time Redundancy Countermeasure for AES , 2015, COSADE.