Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Investigating Efficient Deep Learning Architectures For Side-Channel Attacks on AES (2309.13170v1)

Published 22 Sep 2023 in cs.CR and cs.AI

Abstract: Over the past few years, deep learning has been getting progressively more popular for the exploitation of side-channel vulnerabilities in embedded cryptographic applications, as it offers advantages in terms of the amount of attack traces required for effective key recovery. A number of effective attacks using neural networks have already been published, but reducing their cost in terms of the amount of computing resources and data required is an ever-present goal, which we pursue in this work. We focus on the ANSSI Side-Channel Attack Database (ASCAD), and produce a JAX-based framework for deep-learning-based SCA, with which we reproduce a selection of previous results and build upon them in an attempt to improve their performance. We also investigate the effectiveness of various Transformer-based models.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. ANSSI and CEA “ASCAD: Side Channels Analysis and Deep Learning”, 2019-2021 URL: https://github.com/ANSSI-FR/ASCAD
  2. “Secure AES128 Encryption Implementation for ATmega8515”, 2018 URL: https://github.com/ANSSI-FR/secAES-ATmega8515
  3. “Deep learning for side-channel analysis and introduction to ASCAD database” In Journal of Cryptographic Engineering 10, 2020 DOI: 10.1007/s13389-019-00220-8
  4. “JAX: composable transformations of Python+NumPy programs”, 2018 URL: http://github.com/google/jax
  5. “Language Models are Few-Shot Learners”, 2020 arXiv:2005.14165 [cs.CL]
  6. “Rethinking Attention with Performers”, 2021 arXiv:2009.14794 [cs.LG]
  7. ASCAD Community “Issue 13 - Difference of Datasets: Sampling Frequency / EM & Power?” Accessed: 2022-02-01 URL: https://archive.is/CMSAL
  8. “Wavelet transform based pre-processing for side channel analysis” In Proceedings - 2012 IEEE/ACM 45th International Symposium on Microarchitecture Workshops, MICROW 2012, 2012, pp. 32–38 DOI: 10.1109/MICROW.2012.15
  9. “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding”, 2019 arXiv:1810.04805 [cs.CL]
  10. Pierre Dusart, Gilles Letourneux and Olivier Vivolo “Differential fault analysis on AES” In International Conference on Applied Cryptography and Network Security, 2003, pp. 293–306 Springer
  11. “An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale”, 2021 arXiv:2010.11929 [cs.CV]
  12. “Tiny Transformers for Environmental Sound Classification at the Edge”, 2021 arXiv:2103.12157 [cs.SD]
  13. “Affine Masking against Higher-Order Side Channel Analysis” https://ia.cr/2010/523, Cryptology ePrint Archive, Report 2010/523, 2010
  14. Yuan Gong, Yu-An Chung and James Glass “AST: Audio Spectrogram Transformer”, 2021 arXiv:2104.01778 [cs.SD]
  15. Daniel Genkin, Adi Shamir and Eran Tromer “Acoustic cryptanalysis” In Journal of Cryptology 30.2 Springer, 2017, pp. 392–443
  16. “Deep Residual Learning for Image Recognition”, 2015 arXiv:1512.03385 [cs.CV]
  17. “Haiku: Sonnet for JAX”, 2020 URL: http://github.com/deepmind/dm-haiku
  18. “Optax: composable gradient transformation and optimisation, in JAX!”, 2020 URL: http://github.com/deepmind/optax
  19. Jeremy Howard “The fastai deep learning library” GitHub, https://github.com/fastai/fastai, 2018
  20. “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift”, 2015 arXiv:1502.03167 [cs.LG]
  21. “Averaging Weights Leads to Wider Optima and Better Generalization”, 2019 arXiv:1803.05407 [cs.LG]
  22. “Perceiver IO: A General Architecture for Structured Inputs and Outputs”, 2021 arXiv:2107.14795 [cs.LG]
  23. “Perceiver: General Perception with Iterative Attention”, 2021 arXiv:2103.03206 [cs.CV]
  24. Diederik P. Kingma and Jimmy Ba “Adam: A Method for Stochastic Optimization”, 2017 arXiv:1412.6980 [cs.LG]
  25. Nikita Kitaev, Łukasz Kaiser and Anselm Levskaya “Reformer: The Efficient Transformer”, 2020 arXiv:2001.04451 [cs.LG]
  26. Paul C Kocher “Timing attacks on implementations of Diffie-Hellman, RSA, DSS, and other systems” In Annual International Cryptology Conference, 1996, pp. 104–113 Springer
  27. “Deep Learning for Symbolic Mathematics”, 2019 arXiv:1912.01412 [cs.SC]
  28. “Pay Attention to Raw Traces: A Deep Learning Architecture for End-to-End Profiling Attacks” In IACR Transactions on Cryptographic Hardware and Embedded Systems 2021.3, 2021, pp. 235–274 DOI: 10.46586/tches.v2021.i3.235-274
  29. Loïc Masure, Cécile Dumas and Emmanuel Prouff “Gradient Visualization for General Characterization in Profiling Attacks” In Constructive Side-Channel Analysis and Secure Design - 10th International Workshop, COSADE 2019, Darmstadt, Germany, April 3-5, 2019, Proceedings 11421, Lecture Notes in Computer Science Springer, 2019, pp. 145–167 DOI: 10.1007/978-3-030-16350-1\_9
  30. “Side Channel Analysis against the ANSSI’s protected AES implementation on ARM” https://ia.cr/2021/592, Cryptology ePrint Archive, Report 2021/592, 2021
  31. “Training Tips for the Transformer Model” In The Prague Bulletin of Mathematical Linguistics 110.1 Charles University in Prague, Karolinum Press, 2018, pp. 43–70 DOI: 10.2478/pralin-2018-0002
  32. “Language models are unsupervised multitask learners” In OpenAI blog 1.8, 2019, pp. 9
  33. “Power side-channel attack analysis: A review of 20 years of study for the layman” In Cryptography 4.2 Multidisciplinary Digital Publishing Institute, 2020, pp. 15
  34. Emmanuel Prouff Ryad Benadjila and Adrian Thillar “Hardened Library for AES-128 encryption/decryption on ARM Cortex M4 Achitecture”, 2019 URL: https://github.com/ANSSI-FR/SecAESSTM32/
  35. “Audiomer: A Convolutional Transformer For Keyword Spotting”, 2022 arXiv:2109.10252 [cs.LG]
  36. Leslie N. Smith “Cyclical Learning Rates for Training Neural Networks”, 2017 arXiv:1506.01186 [cs.CV]
  37. Leslie N. Smith “A disciplined approach to neural network hyper-parameters: Part 1 – learning rate, batch size, momentum, and weight decay”, 2018 arXiv:1803.09820 [cs.LG]
  38. Leslie N. Smith and Nicholay Topin “Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates”, 2018 arXiv:1708.07120 [cs.LG]
  39. “Very Deep Convolutional Networks for Large-Scale Image Recognition”, 2015 arXiv:1409.1556 [cs.CV]
  40. “Rethinking the Inception Architecture for Computer Vision”, 2015 arXiv:1512.00567 [cs.CV]
  41. “Attention Is All You Need”, 2017 arXiv:1706.03762 [cs.CL]
  42. “CvT: Introducing Convolutions to Vision Transformers”, 2021 arXiv:2103.15808 [cs.CV]
  43. Yang You, Igor Gitman and Boris Ginsburg “Large Batch Training of Convolutional Networks”, 2017 arXiv:1708.03888 [cs.CV]
  44. “Large Batch Optimization for Deep Learning: Training BERT in 76 minutes”, 2020 arXiv:1904.00962 [cs.LG]
  45. “Methodology for Efficient CNN Architectures in Profiling Attacks” In IACR Transactions on Cryptographic Hardware and Embedded Systems 2020.1, 2019, pp. 1–36 DOI: 10.13154/tches.v2020.i1.1-36
  46. “Ranking Loss: Maximizing the Success Rate in Deep Learning Side-Channel Analysis” In IACR Transactions on Cryptographic Hardware and Embedded Systems 2021.1, 2020, pp. 25–55 DOI: 10.46586/tches.v2021.i1.25-55
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now