Neural-Network-Based Modeling Attacks on XOR Arbiter PUFs Revisited

By revisiting recent neural-network based modeling attacks on XOR Arbiter PUFs from the literature, we show that XOR Arbiter PUFs and Interpose PUFs can be attacked faster, up to larger security parameters, and with orders of magnitude fewer challenge-response pairs than previously known. To support our claim, we discuss the differences and similarities of recently proposed modeling attacks and offer a fair comparison of the performance of these attacks by implementing all of them using the popular machine learning framework Keras and comparing their performance against the well-studied Logistic Regression attack. Our findings show that neural-network-based modeling attacks have the potential to outperform traditional modeling attacks on PUFs and must hence become part of the standard toolbox for PUF security analysis; the code and discussion in this paper can serve as a basis for the extension of our results to PUF designs beyond the scope of this work.

[1]  Debdeep Mukhopadhyay,et al.  SACReD: An Attack Framework on SAC Resistant Delay-PUFs leveraging Bias and Reliability Factors , 2021, 2021 58th ACM/IEEE Design Automation Conference (DAC).

[2]  Georg T. Becker,et al.  Combining Optimization Objectives: New Modeling Attacks on Strong PUFs , 2021, IACR Trans. Cryptogr. Hardw. Embed. Syst..

[3]  Debdeep Mukhopadhyay,et al.  PUF-G: A CAD Framework for Automated Assessment of Provable Learnability from Formal PUF Representations , 2020, 2020 IEEE/ACM International Conference On Computer Aided Design (ICCAD).

[4]  Ahmad O. Aseeri,et al.  A Fast Deep Learning Method for Security Vulnerability Study of XOR PUFs , 2020, Electronics.

[5]  Arindam Sanyal,et al.  0.3 pJ/Bit Machine Learning Resistant Strong PUF Using Subthreshold Voltage Divider Array , 2020, IEEE Transactions on Circuits and Systems II: Express Briefs.

[6]  Michael Orshansky,et al.  A Strong Subthreshold Current Array PUF Resilient to Machine Learning Attacks , 2020, IEEE Transactions on Circuits and Systems I: Regular Papers.

[7]  Amir Moradi,et al.  TI-PUF: Toward Side-Channel Resistant Physical Unclonable Functions , 2020, IEEE Transactions on Information Forensics and Security.

[8]  Ulrich Rührmair,et al.  Splitting the Interpose PUF: A Novel Modeling Attack Strategy , 2020, IACR Cryptol. ePrint Arch..

[9]  Rajat Subhra Chakraborty,et al.  A Computationally Efficient Tensor Regression Network based Modeling Attack on XOR APUF , 2019, 2019 Asian Hardware Oriented Security and Trust Symposium (AsianHOST).

[10]  Ahmad O. Aseeri,et al.  Extensive Examination of XOR Arbiter PUFs as Security Primitives for Resource-Constrained IoT Devices , 2019, 2019 17th International Conference on Privacy, Security and Trust (PST).

[11]  Rajat Subhra Chakraborty,et al.  Deep Learning based Model Building Attacks on Arbiter PUF Compositions , 2019, IACR Cryptol. ePrint Arch..

[12]  Ulrich Rührmair,et al.  The Interpose PUF: Secure PUF Design against State-of-the-art Machine Learning Attacks , 2019, IACR Cryptol. ePrint Arch..

[13]  2018 Asian Hardware Oriented Security and Trust Symposium (AsianHOST) , 2018 .

[14]  Yu Zhuang,et al.  A Machine Learning-Based Security Vulnerability Study on XOR PUFs for Resource-Constraint Internet of Things , 2018, 2018 IEEE International Congress on Internet of Things (ICIOT).

[15]  Olivier Richard,et al.  CONCURRENCY AND COMPUTATION : PRACTICE AND EXPERIENCE , 2018 .

[16]  Ieee Staff.  2018 IEEE International Congress on Internet of Things (ICIOT) , 2018 .

[17]  Yu Zhuang,et al.  Towards fast and accurate machine learning attacks of feed-forward arbiter PUFs , 2017, 2017 IEEE Conference on Dependable and Secure Computing.

[18]  Srinivas Devadas,et al.  Trapdoor Computational Fuzzy Extractors and Stateless Cryptographically-Secure Physical Unclonable Functions , 2017, IEEE Transactions on Dependable and Secure Computing.

[19]  Mitsugu Iwamoto,et al.  Deep-Learning-Based Security Evaluation on Authentication Systems Using Arbiter PUF and Its Variants , 2016, IWSEC.

[20]  Jean-Pierre Seifert,et al.  Strong Machine Learning Attack Against PUFs with No Mathematical Model , 2016, CHES.

[21]  Srinivas Devadas,et al.  A Lockdown Technique to Prevent Machine Learning on PUFs for Lightweight Authentication , 2016, IEEE Transactions on Multi-Scale Computing Systems.

[22]  Georg T. Becker,et al.  The Gap Between Promise and Reality: On the Insecurity of XOR Arbiter PUFs , 2015, CHES.

[23]  Georg T. Becker,et al.  On the Scaling of Machine Learning Attacks on PUFs with Application to Noise Bifurcation , 2015, RFIDSec.

[24]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[25]  Jean-Pierre Seifert,et al.  Physical Characterization of Arbiter PUFs , 2014, IACR Cryptol. ePrint Arch..

[26]  Jeroen Delvaux,et al.  Side channel modeling attacks on 65nm arbiter PUFs exploiting CMOS device noise , 2013, 2013 IEEE International Symposium on Hardware-Oriented Security and Trust (HOST).

[27]  Patrick Groeneveld,et al.  Proceedings of the 49th Annual Design Automation Conference , 2012, DAC 2012.

[28]  Ingrid Verbauwhede,et al.  Radio Frequency Identification. Security and Privacy Issues , 2012, Lecture Notes in Computer Science.

[29]  Srinivas Devadas,et al.  Modeling attacks on physical unclonable functions , 2010, CCS '10.

[30]  G. Edward Suh,et al.  Physical Unclonable Functions for Device Authentication and Secret Key Generation , 2007, 2007 44th ACM/IEEE Design Automation Conference.

[31]  Somesh Jha,et al.  Proceedings of the 15th ACM conference on Computer and communications security , 2005, CCS 2008.

[32]  Bertram E. Shi,et al.  IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS — I : REGULAR PAPERS , VOL . ? ? , NO . ? ? , ? ? ? ? , 2007 .

[33]  Srinivas Devadas,et al.  Identification and authentication of integrated circuits , 2004, Concurr. Pract. Exp..

[34]  Editors , 2003 .

[35]  R. Pappu,et al.  Physical One-Way Functions , 2002, Science.