Real-Time Detection and Categorization of Cache Side-Channel Attacks Using Deep Learning and Morlet Wavelet Assistance
| International Journal of Electronics and Communication Engineering |
| © 2024 by SSRG - IJECE Journal |
| Volume 11 Issue 1 |
| Year of Publication : 2024 |
| Authors : C. Lakshminatha Reddy, K. Malathi |
10.14445/23488549/IJECE-V11I1P102
How to Cite?
C. Lakshminatha Reddy, K. Malathi, "Real-Time Detection and Categorization of Cache Side-Channel Attacks Using Deep Learning and Morlet Wavelet Assistance," SSRG International Journal of Electronics and Communication Engineering, vol. 11, no. 1, pp. 15-27, 2024. Crossref, https://doi.org/10.14445/23488549/IJECE-V11I1P102
Abstract:
Cache Side Channel (CSC) attacks track user’s cache activity to get private data. This attack often targets the L3 cache that the user and the intruder share. As a result, an intruder can gather private data without tipping off the target. The approach for real-time detection of CSC attacks is developed in this research. The proposed method quickly detects CSC attacks after detecting the change in the CPU numbers. To do this, the value of the CPU counters is measured using a Deep Learning (DL) network with Intel Morlet Wavelet assistance and Weighted Mean of Vectors (WMOV) optimization. Understanding the kind of data that is released is crucial for distinguishing and categorizing cache-based side-channel attacks. Timing attacks, commonly referred to as time-driven attacks, produce quantitative implementation data pertaining to timing. Multiple counters captured changes throughout the attack through the course of the research. The work also presents a categorization of these attacks according to the information-leaking source. After that, a qualitative examination of the effectiveness, complexity, and vulnerabilities of the target cryptosystems of these attacks is conducted. The results of the experiments demonstrate that the proposed detection method performs well for real-time detection in a variety of situations.
Keywords:
Attack detection, Cache Side Channel, Deep Learning, Intel Morlet Wavelet assistance, Weighted Mean of Vectors (WMOV) optimization.
References:
[1] Raphael Spreitzer et al., “Systematic Classification of Side-Channel Attacks: A Case Study for Mobile Devices,” IEEE Communications Surveys & Tutorials, vol. 21, no. 1, pp. 465-488, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Hervé Chabanne et al., “Side Channel Attacks for Architecture Extraction of Neural Networks,” CAAI Transactions on Intelligence Technology, vol. 6, no. 1, pp. 3-16, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Shahid Anwar et al., “Cross-VM Cache-Based Side Channel Attacks and Proposed Prevention Mechanisms: A Survey,” Journal of Network and Computer Applications, vol. 93, pp. 259-279, 2017.
[CrossRef] [Publisher Link]
[4] Hoda Naghibijouybari et al., “Rendered Insecure: GPU Side Channel Attacks are Practical,” Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security, pp. 2139-2153, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Benjamin Timon, “Non-Profiled Deep Learning-Based Side-Channel Attacks with Sensitivity Analysis,” IACR Transactions on Cryptographic Hardware and Embedded Systems, vol. 2019, no. 2, pp. 107-131, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Prasanna Ravi et al., “Generic Side-channel Attacks on CCA-Secured Lattice-Based PKE and KEMs,” IACR Transactions on Cryptographic Hardware and Embedded Systems, vol. 2020, no. 3, pp. 307-335, 2020.
[CrossRef] [Publisher Link]
[7] Claude Carlet, and Sylvain Guilley, “Complementary Dual Codes for Counter Measures to Side-Channel Attacks,” Coding Theory and Applications, pp. 97-105, 2015.
[CrossRef] [Publisher Link]
[8] Stephen Crane et al., “Thwarting Cache Side-Channel Attacks through Dynamic Software Diversity,” Proceedings 2015 Network and Distributed System Security Symposiums, San Diego, pp. 1-14, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Peng Cheng et al., “SonarSnoop: Active Acoustic Side-Channel Attacks,” International Journal of Information Security, vol. 19, pp. 213-228, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Xiaodong Yu et al., “Comparative Measurement of Cache Configurations’ Impacts on Cache Timing Side-Channel Attacks,” 12th USENIX Workshop on Cyber Security Experimentation and Test (CSET 19), pp. 1-9, 2019.
[Google Scholar] [Publisher Link]
[11] Yuval Yarom, Daniel Genkin, and Nadia Heninger, “CacheBleed: A Timing Attack on OpenSSL Constant-Time RSA,” Journal of Cryptographic Engineering, vol. 7, pp. 99-112, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Jonghyeon Cho et al., “Real-Time Detection for Cache Side Channel Attack Using Performance Counter Monitor,” Applied Sciences, vol. 10, no. 3, pp. 1-14, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Ben Gras et al., “ABSynthe: Automatic Blackbox Sides-Channel Synthesis on Commodity Microarchitectures,” Network and Distributed Systems Security (NDSS) Symposiums, San Diego, USA, pp. 1-18, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Qian Guo, Andreas Johansson, and Thomas Johansson, “A Key-Recovery Side-Channel Attack on Classic McEliece Implementations,” IACR Transactions on Cryptographic Hardware and Embedded Systems, vol. 2022, no. 4, pp. 800-827, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Anatoly Shusterman et al., “Cache-Based Characterization: A Low-Infrastructure, Distributed Alternative to Network-Based Traffic and Application Characterization,” Computer Networks, vol. 200, 2021.
[CrossRef] [Publisher Link]
[16] Lejla Batina et al., “CSI Neural Network: Using Side-Channels to Recover Your Artificial Neural Network Information,” arXiv, pp. 1-15, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Maria Mushtaq et al., “Winter is Here! A Decade of Cache-Based Side-Channel Attacks, Detection & Mitigation for RSA,” Information Systems, vol. 92, 2020.
[CrossRef] [Google Scholar] [Publisher Link]