Trevor Yap
ABSTRACT
This paper provides a novel perspective on improving the efficiency of side-channel analysis by applying two deep feature loss functions: Soft Nearest Neighbor (SoftNN) and Center loss. By leveraging these loss functions during the deep neural networks (DNNs) training phase, our study illuminates how profiling attacks can be more powerful. Deep feature loss functions incorporate the outputs from the DNN's intermediate layers into their computations, which reduces the distance between similar data points. As such, these techniques enhance the DNN's ability to generate more precise and meaningful representations, thereby improving its discriminative power. This paper presents empirical evidence illustrating the effectiveness of SoftNN and Center loss in strengthening DNN-based side-channel attacks. For instance, when using Center loss together with the focal loss ratio (FLR), it requires the least number of traces to break the ASCADf dataset. On the other hand, applying SoftNN with FLR successfully recovers the key for the ASCADr dataset with the least traces. The insights presented in this study can act as a baseline for more advanced investigations into the utility of such loss functions in deep learning-based side-channel analysis.
- Ryad Benadjila, Emmanuel Prouff, Ré mi Strullu, Eleonora Cagli, and Cé cile Dumas. 2020. Deep learning for side-channel analysis and introduction to ASCAD database. J. Cryptogr. Eng. , Vol. 10, 2 (2020), 163--188. https://doi.org/10.1007/s13389-019-00220--8Google Scholar
Cross Ref
- Eleonora Cagli, Cécile Dumas, and Emmanuel Prouff. 2017. Convolutional Neural Networks with Data Augmentation Against Jitter-Based Countermeasures. In Cryptographic Hardware and Embedded Systems -- CHES 2017, Wieland Fischer and Naofumi Homma (Eds.). Springer International Publishing, Cham, 45--68.Google ScholarCross Ref
- Morris Dworkin, Elaine Barker, James Nechvatal, James Foti, Lawrence Bassham, E. Roback, and James Dray. 2001. Advanced Encryption Standard (AES). https://doi.org/10.6028/NIST.FIPS.197Google ScholarCross Ref
- Nicholas Frosst, Nicolas Papernot, and Geoffrey Hinton. 2019. Analyzing and Improving Representations with the Soft Nearest Neighbor Loss. arxiv: 1902.01889 [stat.ML]Google Scholar
- Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. MIT Press. http://www.deeplearningbook.org.Google ScholarDigital Library
- Maikel Kerkhof, Lichao Wu, Guilherme Perin, and Stjepan Picek. 2022. Focus is Key to Success: A Focal Loss Function for Deep Learning-Based Side-Channel Analysis. In Constructive Side-Channel Analysis and Secure Design, Josep Balasch and Colin O'Flynn (Eds.). Springer International Publishing, Cham, 29--48.Google Scholar
- Maikel Kerkhof, Lichao Wu, Guilherme Perin, and Stjepan Picek. 2023. No (good) loss no gain: systematic evaluation of loss functions in deep learning-based side-channel analysis. Journal of Cryptographic Engineering , Vol. 13, 3 (May 2023), 311--324. https://doi.org/10.1007/s13389-023-00320--6Google ScholarCross Ref
- Kussul, Nataliia and Lavreniuk, Mykola and Skakun, Sergii and Shelestov, Andrii. 2017. Deep Learning Classification of Land Cover and Crop Types Using Remote Sensing Data. IEEE Geoscience and Remote Sensing Letters , Vol. 14, 5 (2017), 778--782. https://doi.org/10.1109/LGRS.2017.2681128Google ScholarCross Ref
- Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. 2017. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision. 2980--2988.Google ScholarCross Ref
- Lo"ic Masure, Cécile Dumas, and Emmanuel Prouff. 2020. A comprehensive study of deep learning for side-channel analysis. IACR Transactions on Cryptographic Hardware and Embedded Systems (2020), 348--375.Google Scholar
- Colin O'Flynn and Zhizhang David Chen. 2014. ChipWhisperer: An Open-Source Platform for Hardware Embedded Security Research. In International Workshop on Constructive Side-Channel Analysis and Secure Design.Google Scholar
- Guilherme Perin, Lichao Wu, and Stjepan Picek. 2022a. Exploring Feature Selection Scenarios for Deep Learning-based Side-channel Analysis. IACR Transactions on Cryptographic Hardware and Embedded Systems, Vol. 2022, 4 (Aug. 2022), 828--861. https://doi.org/10.46586/tches.v2022.i4.828--861Google ScholarCross Ref
- Guilherme Perin, Lichao Wu, and Stjepan Picek. 2022b. I Know What Your Layers Did: Layer-wise Explainability of Deep Learning Side-channel Analysis. Cryptology ePrint Archive, Paper 2022/1087. https://eprint.iacr.org/2022/1087 https://eprint.iacr.org/2022/1087.Google Scholar
- Stjepan Picek, Annelie Heuser, Alan Jovic, Shivam Bhasin, and Francesco Regazzoni. 2018. The Curse of Class Imbalance and Conflicting Metrics with Machine Learning for Side-channel Evaluations, volume=2019. IACR Transactions on Cryptographic Hardware and Embedded Systems 1 (Nov. 2018), 209--237. https://doi.org/10.13154/tches.v2019.i1.209--237Google ScholarCross Ref
- Stjepan Picek, Guilherme Perin, Luca Mariot, Lichao Wu, and Lejla Batina. 2023. SoK: Deep Learning-Based Physical Side-Channel Analysis. ACM Comput. Surv. , Vol. 55, 11, Article 227 (feb 2023), bibinfonumpages35 pages. https://doi.org/10.1145/3569577Google ScholarDigital Library
- Jorai Rijsdijk, Lichao Wu, Guilherme Perin, and Stjepan Picek. 2021. Reinforcement Learning for Hyperparameter Tuning in Deep Learning-based Side-channel Analysis. IACR Transactions on Cryptographic Hardware and Embedded Systems, Vol. 2021, 3 (Jul. 2021), 677--707. https://doi.org/10.46586/tches.v2021.i3.677--707Google ScholarCross Ref
- Ruslan Salakhutdinov and Geoff Hinton. 2007. Learning a Nonlinear Embedding by Preserving Class Neighbourhood Structure. In Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research, Vol. 2), Marina Meila and Xiaotong Shen (Eds.). PMLR, San Juan, Puerto Rico, 412--419. https://proceedings.mlr.press/v2/salakhutdinov07a.htmlGoogle Scholar
- Yandong Wen, Kaipeng Zhang, Zhifeng Li, and Yu Qiao. 2016. A Discriminative Feature Learning Approach for Deep Face Recognition. In Computer Vision -- ECCV 2016, Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling (Eds.). Springer International Publishing, Cham, 499--515.Google ScholarCross Ref
- Lichao Wu, Guilherme Perin, and Stjepan Picek. 2022a. I Choose You: Automated Hyperparameter Tuning for Deep Learning-based Side-channel Analysis. IEEE Transactions on Emerging Topics in Computing (2022), 1--12. https://doi.org/10.1109/TETC.2022.3218372Google ScholarCross Ref
- Lichao Wu, Guilherme Perin, and Stjepan Picek. 2022b. The Best of Two Worlds: Deep Learning-assisted Template Attack. IACR Transactions on Cryptographic Hardware and Embedded Systems, Vol. 2022, 3 (Jun. 2022), 413--437. https://doi.org/10.46586/tches.v2022.i3.413--437Google ScholarCross Ref
- Baoguo Yuan, Junfeng Wang, Dong Liu, Wen Guo, Peng Wu, and Xuhua Bao. 2020. Byte-level malware classification based on markov images and deep learning. Computers & Security , Vol. 92 (2020), 101740. https://doi.org/10.1016/j.cose.2020.101740Google ScholarCross Ref
- Gabriel Zaid, Lilian Bossuet, François Dassance, Amaury Habrard, and Alexandre Venelli. 2020. Ranking Loss: Maximizing the Success Rate in Deep Learning Side-Channel Analysis. IACR Transactions on Cryptographic Hardware and Embedded Systems, Vol. 2021, 1 (Dec. 2020), 25--55. https://doi.org/10.46586/tches.v2021.i1.25--55Google ScholarCross Ref
- Gabriel Zaid, Lilian Bossuet, Amaury Habrard, and Alexandre Venelli. 2019. Methodology for Efficient CNN Architectures in Profiling Attacks. IACR Transactions on Cryptographic Hardware and Embedded Systems, Vol. 2020, 1 (Nov. 2019), 1--36. https://doi.org/10.13154/tches.v2020.i1.1--36Google ScholarCross Ref
- Jiajia Zhang, Mengce Zheng, Jiehui Nan, Honggang Hu, and Nenghai Yu. 2020. A Novel Evaluation Metric for Deep Learning-Based Side Channel Analysis and Its Extended Application to Imbalanced Data. IACR Transactions on Cryptographic Hardware and Embedded Systems, Vol. 2020, 3 (Jun. 2020), 73--96. https://doi.org/10.13154/tches.v2020.i3.73--96 ioGoogle ScholarCross Ref
Index Terms
- Beyond the Last Layer: Deep Feature Loss Functions in Side-channel Analysis
Recommendations
Focus is Key to Success: A Focal Loss Function for Deep Learning-Based Side-Channel Analysis
Constructive Side-Channel Analysis and Secure DesignAbstractThe deep learning-based side-channel analysis represents one of the most powerful side-channel attack approaches. Thanks to its capability in dealing with raw features and countermeasures, it becomes the de facto standard approach for the SCA ...
Reinforcement Learning-Based Design of Side-Channel Countermeasures
Security, Privacy, and Applied Cryptography EngineeringAbstractDeep learning-based side-channel attacks are capable of breaking targets protected with countermeasures. The constant progress in the last few years makes the attacks more powerful, requiring fewer traces to break a target. Unfortunately, to ...
Portability of Deep-Learning Side-Channel Attacks against Software Discrepancies
WiSec '23: Proceedings of the 16th ACM Conference on Security and Privacy in Wireless and Mobile NetworksDeep-learning side-channel attacks can reveal encryption keys on a device by analyzing power consumption with neural networks. However, the portability of deep-learning side-channel attacks can be affected when training data (from the training device) ...
Comments