Abstract
Recently, machine learning algorithms have been utilized by system defenders and attackers to secure and attack hardware, respectively. In this work, we investigate the impact of machine learning on hardware security. We explore the defense and attack mechanisms for hardware that are based on machine learning. Moreover, we identify suitable machine learning algorithms for each category of hardware security problems. Finally, we highlight some important aspects related to the application of machine learning to hardware security problems and show how the practice of applying machine learning to hardware security problems has changed over the past decade.
Similar content being viewed by others
References
Alam MM, Tehranipoor M, Forte D (2016) Recycled FPGA detection using exhaustive LUT path delay characterization. In: Proceedings of ITC, pp 1–10
Ankerst M, Breunig MM, Kriegel HP, Sander J (1999) OPTICS: ordering points to identify the clustering structure. In: ACM Sigmod record, vol 28, no. 2, pp 49–60
Asadizanjani N, Tehranipoor M, Forte D (2017) Counterfeit electronics detection using image processing and machine learning. In: Journal of physics: conference series, vol 787, no. 1, p. 012023
Baldi P (2012) Autoencoders, unsupervised learning, and deep architectures. In: Proceedings of ICML workshop on unsupervised and transfer learning, pp 37–49
Bao C, Forte D, Srivastava A (2014) On application of one-class svm to reverse engineering-based hardware trojan detection. In: Proceedings of fifteenth international symposium on quality electronic design, pp 47–54
Bao C, Forte D, Srivastava A (2016) On reverse engineering-based hardware trojan detection. IEEE Trans Comput Aided Des Integr Circuits Syst 35(1):49–57
Barker WC, Barker E et al. (2012) Recommendation for the triple data encryption algorithm (tdea) block cipher: Nist special publication 800-67, revision 2
Basak D, Pal S, Patranabis DC (2007) Support vector regression. Neural Information Processing-Letters and Reviews 11(10):203–224
Çakir B, Malik S (2015) Hardware Trojan detection for gate-level ICs using signal correlation based clustering. In: Proceedings of DATE, pp 471–476
Carvalho VR, Cohen WW (2006) Single-pass online learning: performance, voting schemes and online feature selection. In: Proceedings of ACM SIGKDD. ACM, pp 548–553
Chari S, Rao JR, Rohatgi P (2002) Template attacks. In: CHES. Springer, pp 13–28
Chen Q, Csaba G, Lugli P, Schlichtmann U, Rührmair U (2011) The bistable ring puf: a new architecture for strong physical unclonable functions. In: Proceedings of HOST. IEEE, pp 134– 141
Chen X, Wang L, Wang Y, Liu Y, Yang H (2017) A general framework for hardware trojan detection in digital circuits by statistical learning algorithms. IEEE Trans Comput Aided Des Integr Circuits Syst 36(10):1633–1646
Choudary O, Kuhn MG (2013) Efficient template attacks. In: CARDIS. Springer, pp 253–270
Cox DR (1958) The regression analysis of binary sequences. J R Stat Soc Ser B Methodol 20(2):215–242
Crammer K, Singer Y (2001) On the algorithmic implementation of multiclass kernel-based vector machines. J Mach Learn Res 2(Dec):265–292
Daemen J, Rijmen V (2001) Specification for the advanced encryption standard (aes). Federal Information Processing Standards Publication, vol 197
Dogan H, Forte D, Tehranipoor MM (2014) Aging analysis for recycled FPGA detection. In: Proceedings of DFT, pp 171–176
Eisenbarth T, Paar C, Weghenkel B (2010) Building a side channel based disassembler. In: Transactions on computational science x. Springer, pp 78–99
Elnaggar R, Chakrabarty K, Tahoori MB (2017) Run-time hardware trojan detection using performance counters. In: Proceedings of ITC, pp 1–10
Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119–139
Friedman JH (1991) Multivariate adaptive regression splines. Ann Stat 19(1):1–67
Ganji F, Tajik S, Seifert J-P (2015) Let me prove it to you: Ro pufs are provably learnable. In: ICISC. Springer, pp 345–358
Ganji F, Tajik S, Seifert J-P (2015) Why attackers win: on the learnability of xor arbiter pufs. In: Trust. Springer, pp 22–39
Ganji F, Tajik S, Fäßler F, Seifert J-P (2016) Strong machine learning attack against pufs with no mathematical model. In: Proceedings of CHES. Springer, pp 391–411
Ganji F, Tajik S, Seifert J-P (2016) Pac learning of arbiter pufs. J Cryptogr Eng 6(3):249–258
Gers FA, Schraudolph NN, Schmidhuber J (2002) Learning precise timing with lstm recurrent networks. J Mach Learn Res 3(Aug):115–143
Guin U, DiMase D, Tehranipoor M (2014) Counterfeit integrated circuits: detection, avoidance, and the challenges ahead. J Electron Test 30(1):9–23
Hartigan JA, Wong MA (1979) Algorithm as 136: a k-means clustering algorithm. J R Stat Soc: Ser C: Appl Stat 28(1):100– 108
Hasegawa K, Oya M, Yanagisawa M, Togawa N (2016) Hardware Trojans classification for gate-level netlists based on machine learning. In: Proceedings of IOLTS, pp 203–206
Hasegawa K, Yanagisawa M, Togawa N (2017) Trojan-feature extraction at gate-level netlists and its application to hardware-trojan detection using random forest classifier. In: Proceedings of ISCAS. IEEE, pp 1–4
Hassoun MH (1995) Fundamentals of artificial neural networks. MIT Press, Cambridge
Hearst MA, Dumais ST, Osuna E, Platt J, Scholkopf B (1998) Support vector machines. IEEE Intelligent Systems and Their Applications 13(4):18–28
Heuser A, Zohner M (2012) Intelligent machine homicide. In: COSADE. Springer, pp 249–264
Heyszl J, Ibing A, Mangard S, De Santis F, Sigl G (2013) Clustering algorithms for non-profiled single-execution attacks on exponentiations. In: CARDIS. Springer, pp 79–93
Ho TK (1995) Random decision forests. In: Proceedings of the third international conference on document analysis and recognition, vol 1. IEEE, pp 278–282
Hospodar G, Gierlichs B, De Mulder E, Verbauwhede I, Vandewalle J (2011) Machine learning in side-channel analysis: a first study. J Cryptogr Eng 1(4):293–302
Huang K, Carulli JM, Makris Y (2012) Parametric counterfeit IC detection via support vector machines. In: Proceedings of DFT, pp 7–12
Huang L, Joseph AD, Nelson B, Rubinstein BI, Tygar J (2011) Adversarial machine learning. In: Proceedings of the 4th ACM workshop on security and artificial intelligence. ACM, pp 43–58
Iwase T, Nozaki Y, Yoshikawa M, Kumaki T (2015) Detection technique for hardware Trojans using machine learning in frequency domain. In: Proceedings GCCE. IEEE, pp 185–186
Jap D, Stöttinger M, Bhasin S (2015) Support vector regression: exploiting machine learning techniques for leakage modeling. In: Proceedings of HASP. ACM, p 2
Jin Y, Maliuk D, Makris Y (2012) Post-deployment trust evaluation in wireless cryptographic ICs. In: Proceedings of DATE, pp 965–970
Kaufman L, Rousseeuw PJ (1990) Partitioning around medoids (program pam). Finding groups in data: an introduction to cluster analysis, pp 68–125
Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In: IJCAI. Morgan Kaufmann Publishers Inc., pp 1137–1143
Kohonen T (1998) The self-organizing map. Neurocomputing 21(1–3):1–6
Kulkarni A, Pino Y, French M, Mohsenin T (2016) Real-time anomaly detection framework for many-core router through machine-learning techniques. ACM Journal on Emerging Technologies in Computing Systems (JETC) 13(1):10
Kulkarni A, Pino Y, Mohsenin T (2016) SVM-based real-time hardware trojan detection for many-core platform. In: Proceedings of ISQED, pp 362–367
Kulkarni A, Pino Y, Mohsenin T (2016) Adaptive real-time Trojan detection framework through machine learning. In: Proceedings of HOST. IEEE, pp 120–123
Lamichhane K, Moreno C, Fischmeister S (2018) Non-intrusive program tracing of non-preemptive multitasking systems using power consumption. In: Proceedings of DATE. Dresden, Germany
LeCun Y, Bengio Y (1995) Convolutional networks for images, speech, and time-series. In: Arbib MA (ed) The handbook of brain theory and neural networks. MIT Press
Lerman L, Bontempi G, Markowitch O (2011) Side channel attack: an approach based on machine learning. Center for Advanced Security Research Darmstadt. 29–41
Lerman L, Bontempi G, Taieb SB, Markowitch O (2013) A time series approach for profiling attack. In: SPACE. Springer, pp 75–94
Lerman L, Medeiros SF, Veshchikov N, Meuter C, Bontempi G, Markowitch O (2013) Semi-supervised template attack. In: COSAD. Springer, pp 184–199
Lerman L, Poussier R, Bontempi G, Markowitch O, Standaert F-X (2015) Template attacks vs. machine learning revisited (and the curse of dimensionality in side-channel analysis). In: COSADE. Springer, pp 20–33
Li J, Cheng J-H, Shi J-Y, Huang F (2012) Brief introduction of back propagation (bp) neural network algorithm and its improvement. In: Advances in computer science and information engineering. Springer, pp 553–558
Li J, Ni L, Chen J, Zhou E (2016) A novel hardware trojan detection based on bp neural network. In: 2016 2nd IEEE international conference on proc. computer and communications (ICCC). IEEE, pp 2790–2794
Liu Y, Huang K, Makris Y (2014) Hardware trojan detection through golden chip-free statistical side-channel fingerprinting. In: Proceedings of DAC. ACM, pp 1–6
Liu Y, Jin Y, Nosratinia A, Makris Y (2017) Silicon demonstration of hardware trojan design and detection in wireless cryptographic ICs. VLSI 25(4):1506–1519
Loh W-Y (2011) Classification and regression trees. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 1(1):14–23
Maghrebi H, Portigliatti T, Prouff E (2016) Breaking cryptographic implementations using deep learning techniques. In: SPACE. Springer, pp 3–26
Mandic DP, Chambers JA et al. (2001) Recurrent neural networks for prediction: learning algorithms, architectures and stability. Wiley Online Library
Martinasek Z, Zeman V (2013) Innovative method of the power analysis. Radioengineering 22(2):586–594
Martinasek Z, Hajny J, Malina L (2013) Optimization of power analysis using neural network. In: CARDIS. Springer, pp 94–107
Menezes AJ (2012) Elliptic curve public key cryptosystems, vol 234. Springer Science & Business Media, Berlin
Montgomery DC, Peck EA, Vining GG (2012) Introduction to linear regression analysis, vol 821. Wiley, New York
O’Donnell R (2014) Analysis of boolean functions. Cambridge University Press, Cambridge
Peng H, Long F, Ding C (2005) Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. TPAMI 27(8):1226–1238
Quadir SE, Chen J, Forte D, Asadizanjani N, Shahbazmohamadi S, Wang L, Chandy J, Tehranipoor M (2016) A survey on chip to system reverse engineering. JETC 13(1):6
Quinlan JR (1986) Induction of decision trees. Mach Learn 1(1):81–106
Quinlan JR (2014) C4. 5: programs for machine learning. Elsevier, Amsterdam
Rivest RL (1987) Learning decision lists. Mach Learn 2(3):229–246
Rivest RL (1991) Cryptography and machine learning. In: ASIACRYPT. Springer, pp 427–439
Rostami M, Koushanfar F, Karri R (2014) A primer on hardware security: models, methods, and metrics. Proc IEEE 102(8):1283–1295
Rührmair U, Sehnke F, Sölter J, Dror G, Devadas S, Schmidhuber J (2010) Modeling attacks on physical unclonable functions. In: Proceedings of CCS. ACM, pp 237–249
Rührmair U, Sölter J, Sehnke F, Xu X, Mahmoud A, Stoyanova V, Dror G, Schmidhuber J, Burleson W, Devadas S (2013) Puf modeling attacks on simulated and silicon data. IEEE Trans Inf Forensics Secur 8(11):1876–1891
Salmani H (2017) COTD: reference-free hardware trojan detection and recovery based on controllability and observability in gate-level netlist. IEEE Trans Inf Forensics Secur 12(2):338–350
Schölkopf B, Burges CJ, Smola AJ (1999) Advances in kernel methods: support vector learning. MIT Press, Cambridge
Schölkopf B, Smola AJ, Williamson RC, Bartlett PL (2000) New support vector algorithms. Neural Comput 12(5):1207–1245
Scholkopf B, Sung K-K, Burges CJ, Girosi F, Niyogi P, Poggio T, Vapnik V (1997) Comparing support vector machines with gaussian kernels to radial basis function classifiers. IEEE Trans Signal Process 45 (11):2758–2765
Schuster D, Hesselbarth R (2014) Evaluation of bistable ring pufs using single layer neural networks. In: Proceedings of the international conference on trust and trustworthy computing. Springer, pp 101–109
Shourong H, Yujie Z, Hongming L, Nianhao Z (2017) Wavelet support vector machine algorithm in power analysis attacks. Radioengineering 26(3):890–902
Skabar A (2003) Single-class classifier learning using neural networks: an application to the prediction of mineral deposits. In: ICMLC, vol 4. IEEE, pp 2127–2132
Spoild: side-channel power-based instruction-level disassembler. http://www.hostsymposium.org/host2017/hwdemo/HOST_2017_hwdemo_4.pdf. Accessed 15 Apr 2018
Standaert F-X (2010) Introduction to side-channel attacks. In: Secure integrated circuits and systems. Springer, pp 27–42
Standaert F-X, Koeune F, Schindler W (2009) How to compare profiled side-channel attacks?. In: ACNS. Springer, pp 485–498
Standaert F-X, Malkin TG, Yung M (2009) A unified framework for the analysis of side-channel key recovery attacks. In: Annual international conference on the theory and applications of cryptographic techniques. Springer, pp 443–461
Tan SC, Ting KM, Liu TF (2011) Fast anomaly detection for streaming data. In: Proceedings of IJCAI, pp 1511–1516
Tax DM, Duin RP (2004) Support vector data description. Mach Learn 54(1):45–66
Wold S, Esbensen K, Geladi P (1987) Principal component analysis. Chemom Intell Lab Syst 2 (1–3):37–52
Xiao K, Forte D, Jin Y, Karri R, Bhunia S, Tehranipoor M (2016) Hardware trojans: lessons learned after one decade of research. TODAES 22(1):6
Xue M, Wang J, Hux A (2016) An enhanced classification-based golden chips-free hardware trojan detection technique. In: Proceedings of Asian HOST, pp 1–6
Author information
Authors and Affiliations
Corresponding author
Additional information
Responsible Editor: M. Tehranipoor
Rights and permissions
About this article
Cite this article
Elnaggar, R., Chakrabarty, K. Machine Learning for Hardware Security: Opportunities and Risks. J Electron Test 34, 183–201 (2018). https://doi.org/10.1007/s10836-018-5726-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10836-018-5726-9