본문 바로가기
KERD
논문KCI 등재

딥러닝을 이용한 부채널 데이터 압축 프레임 워크

Side-Channel Archive Framework Using Deep Learning-Based Leakage Compression

김희석|진성현|정상윤
한국정보보호학회 (Korea Institute Of Information Security And Cryptology)|2024.06|정보보호학회논문지 (Journal of The Korea Institute of Information Security and Cryptology)|제34권 제3호|pp. 379-392|DOI https://doi.org/10.13089/JKIISC.2024.34.3.379

0

조회

0

다운로드

0

인용

0

참고문헌

키워드

Deep learningAutoencoderCompressionSide-Channel Analysis
주제분류컴퓨터학

초록

데이터의 급속한 증가와 함께 저장 공간 절약과 데이터 전송의 효율성이 중요한 문제로 대두되면서, 데이터 압축 기술의 효율성 연구가 중요해졌다. 무손실 알고리즘은 원본 데이터를 정확히 복원할 수 있지만, 압축 비율이 제한적이며, 손실 알고리즘은 높은 압축률을 제공하지만 데이터의 일부 손실을 수반한다. 이에 딥러닝 기반 압축 알고리즘, 특히 오토인코더 모델이 데이터 압축 분야에서 활발한 연구가 진행됐다. 본 연구에서는 오토인코더를 활용한 새로운 부채널 분석 데이터 압축기를 제안한다. 제안하는 부채널 데이터 대상 압축기는 부채널데이터 특성을 잘 유지할 뿐만 아니라, 기존의 널리 사용되는 Delfate 압축방식 대비 높은 압축률을 보인다. 로컬 연결 레이어를 사용한 인코더는 부채널 데이터의 시점별 특성을 효과적으로 보존하고, 디코더는 멀티 레이어 퍼셉트론을 사용하여 빠른 압축 해제 시간을 유지한다. 상관 전력 분석을 통해 제안된 압축기가 부채널 데이터의 특성을 손실 없이 데이터 압축이 가능을 증명하였다.

Abstract

With the rapid increase in data, saving storage space and improving the efficiency of data transmission have become critical issues, making the research on the efficiency of data compression technologies increasingly important. Lossless algorithms can precisely restore original data but have limited compression ratios, whereas lossy algorithms provide higher compression rates at the expense of some data loss. There has been active research in data compression using deep learning-based algorithms, especially the autoencoder model. This study proposes a new side-channel analysis data compressor utilizing autoencoders. This compressor achieves higher compression rates than Deflate while maintaining the characteristics of side-channel data. The encoder, using locally connected layers, effectively preserves the temporal characteristics of side-channel data, and the decoder maintains fast decompression times with a multi-layer perceptron. Through correlation power analysis, the proposed compressor has been proven to compress data without losing the characteristics of side-channel data.

참고문헌 (55)

  1. Deutsch, "DEFLATE compressed data format specification version 1.3. No. rfc1951", ~ (1996)
  2. Deutsch, "GZIP file format specification version 4.3. No. rfc1952", ~ (1996)
  3. Burtscher, Martin, "FPC: A high-speed compressor for double-precision floating-point data", IEEE transactions on computers, 58(1), pp.18~31 (2009)
  4. Di, Sheng, "Fast error-bounded lossy HPC data compression with SZ", 2016 ieee international parallel and distributed processing symposium (ipdps), pp.730~739 (2016), IEEE
  5. Lindstrom, "Fixed-rate compressed floating-point arrays", IEEE transactions on visualization and computer graphics, 20(12), pp.2674~2683 (2014)
  6. Lakshminarasimhan, Sriram, "Compressing the incompressible with ISABELA: In-situ reduction of spatio-temporal data", Euro-Par 2011Parallel Processing: 17th International Conference, Euro-Par 2011, pp.366~379 (2011)
  7. Wallace, "The JPEG still picture compression standard", Communications of the ACM, 34(4), pp.30~44 (1992)
  8. Le Gall, "MPEG: A video compression standard for multimedia applications", Communications of the ACM, 34(4), pp.253~262
  9. Dávid Sztahó, "Deep learning solution for pathological voice detection using LSTM-based autoencoder hybrid with multi-task learning", I14th International Joint Conference on Biomedical Engineering Systems and Technologies, pp.135~141 (2021)
  10. Otter, Daniel W, "A survey of the usages of deep learning for natural language processing", IEEE transactions on neural networks and learning systems, 32(2), pp.604~624 (2020)
  11. Hinton, Geoffrey E., "Reducing the dimensionality of data with neural networks", science, 313(5786), pp.504~507 (2006)
  12. Pawar, "Noise reduction in images using autoencoders", 20203rd International Conference on Intelligent Sustainable Systems (ICISS), pp.987~990 (2020), IEEE
  14. Tien, Chin-Wei, "Using autoencoders for anomaly detection and transfer learning in IoT", Computers, 10(7), pp.88~ (2021)
  15. Liu, Tong, "High-ratio lossy compression: Exploring the autoencoder to compress scientific data", IEEE Transactions on Big Data, 9(1), pp.22~36 (2021)
  16. Sento, "Image compression with auto-encoder algorithm using deep neural network (DNN)", 2016Management and Innovation Technology International Conference (MITicon), pp.99~133 (2016), IEEE
  17. Momenifar, Mohammadreza, "A physics-informed vector quantized autoencoder for data compression of turbulent flow", 2022Data Compression Conference (DCC), pp.1~10 (2022), IEEE
  18. Lou, Xiaoxuan, "A survey of microarchitectural side-channel vulnerabilities, attacks, and defenses in cryptography", ACM Computing Surveys (CSUR), 54(6), pp.1~37 (2022)
  19. Khan, Haider Adnan, "IDEA: Intrusion detection through electromagnetic-signal analysis for critical embedded and cyber-physical systems", IEEE Transactions on Dependable and Secure Computing, 18(3), pp.1150~1163 (2019)
  20. Sehatbakhsh, Nader, "REMOTE: Robust external malware detection framework by using electromagnetic signals", IEEE Transactions on Computers, 69(3), pp.312~326 (2019)
  21. Chen, Yu-hsin, "Locally-connected and convolutional neural networks for small footprint speaker recognition", Sixteenth Annual Conference of the International Speech Communication Association (2015)
  22. Driss, S. Ben, "A comparison study between MLP and convolutional neural network models for character recognition", Real-Time Image and Video Processing 2017, 10223, pp.32~42 (2017)
  23. Maghrebi, Houssem, "Breaking cryptographic implementations using deep learning techniques", Security, Privacy, and Applied Cryptography Engineering:6th International Conference, SPACE 2016, pp.3~26 (2016), Springer International Publishing
  24. Cagli, Eleonora, "Convolutional neural networks with data augmentation against jitter-based countermeasures: Profiling attacks without pre-processing", Cryptographic Hardware and Embedded Systems–CHES 2017: 19th International Conference, pp.45~68 (2017)
  25. Kim, Jaehun, "Make some noise. unleashing the power of convolutional neural networks for profiled side-channel analysis", IACR Transactions on Cryptographic Hardware and Embedded Systems, pp.148~179 (2019)
  26. Das, Debayan, "X-DeepSCA: Cross-device deep learning side channel attack", Proceedings of the 56th Annual Design Automation Conference 2019, pp.1~6 (2019)
  27. Timon, "Non-profiled deep learning-based side-channel attacks with sensitivity analysis", IACR Transactions on Cryptographic Hardware and Embedded Systems, pp.107~131 (2019)
  28. Kwon, Donggeun, "Optimizing implementations of non-profiled deep learning-based side-channel attacks", IEEE Access, pp.5957~5967 (2022)
  29. Kwon, Donggeun, "Non-profiled deep learning-based side-channel preprocessing with autoencoders", IEEE Access, 9, pp.57692~57703 (2021)
  30. Wold, Svante, "Principal component analysis", Chemometrics and intelligent laboratory systems, 2(1-3), pp.37~52 (1987)
  31. Standaert, François-Xavier, "Using subspace-based template attacks to compare and combine power and electromagnetic information leakages", International Workshop on Cryptographic Hardware and Embedded Systems, pp.421~425 (2008), Springer Berlin Heidelberg
  33. Goodfellow, Ian, "Advances in neural information processing systems 27" (2014)
  34. Zhou, Yuanyuan, "Deep learning mitigates but does not annihilate the need of aligned traces and a generalized resnet model for side-channel attacks", Journal of Cryptographic Engineering, 10(1), pp.85~95 (2020)
  35. Paguada, Servio, "Toward practical autoencoder-based side-channel analysis evaluations", Computer Networks, 196 (2021)
  36. Ramezanpour, Keyvan, "SCAUL: Power side-channel analysis with unsupervised learning", IEEE Transactions on Computers, 69(11), pp.1626~1638 (2020)
  37. Perin, Guilherme, "Exploring feature selection scenarios for deep learning-based side-channel analysis", IACR Transactions on Cryptographic Hardware and Embedded Systems, 2022(4), pp.828~861 (2022)
  38. Li Mu, "Learning convolutional networks for content-weighted image compression", Proceedings of the IEEE conference on computer vision and pattern recognition, pp.3214~3223 (2018)
  39. Liu Tong, "High-ratio lossy compression:Exploring the autoencoder to compress scientific data", IEEE Transactions on Big Data, 9(1), pp.22~36 (2021)
  40. Alexandre, David, "An autoencoder-based learned image compressor: Description of challenge proposal by NCTU", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp.2539~2542 (2019)
  41. Cheng, Zhengxue, "Energy compaction-based image compression using convolutional autoencoder", IEEE Transactions on Multimedia, 22(4), pp.860~873 (2020)
  42. Fournier, Quentin, "Empirical comparison between autoencoders and traditional dimensionality reduction methods", 2019 IEEE Second International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), pp.211~214 (2019), IEEE
  43. Lempel, Abraham, "On the complexity of finite sequences", IEEE Transactions on information theory, 22(1), pp.75~81 (1976)
  44. Huffman, David A, "A method for the construction of minimum-redundancy codes", Proceedings of the IRE, 40(9), pp.1098~1101 (1952)
  45. Kocher, Paul, "Differential power analysism", Advances in Cryptology—CRYPTO’99: 19th Annual International Cryptology Conference Santa Barbara (1999), Springer Berlin Heidelberg
  46. Brier, Eric, "Correlation power analysis with a leakage model", Cryptographic Hardware and Embedded Systems-CHES 2004: 6th International Workshop Cambridge, pp.16~29 (2004), Springer Berlin Heidelberg
  47. Marcellin, Michael W, "An overview of JPEG-2000", Proceedings DCC 2000. Data compression conference, pp.3~48 (2002), IEEE
  48. MGK: Grizzly:power-analysis traces for an 8-bit load instruction, "Choudary, Omar", ~ (2017)
  49. Benadjila, Ryad, "Deep learning for side-channel analysis and introduction to ASCAD database", Journal of Cryptographic Engineering, 10(2), pp.163~188 (2020)
  50. Goller, Gabriel, "International Workshop on Constructive Side-Channel Analysis and Secure Design", pp.255~270 (2015), Springer International Publishing
  51. Krupa, M, "Precise Digital Integration of Fast Analogue Signals Using a 12-bit Oscilloscope", Proceedings of 3rd International Beam Instrumentation Conference (IBIC 2014), pp.584~586 (2014)
  52. Graa, Mariem, "Detection of side channel attacks based on data tainting in android systems", ICT Systems Security and Privacy Protection: 32nd IFIP TC 11International Conference, SEC 2017, pp.205~218 (2017), Springer International Publishing
  54. Ranzato, Marc'Aurelio, "Sparse feature learning for deep belief networks", Advances in neural information processing systems, 20 (2008)
  55. O’flynn, Colin, "Chipwhisperer: An open-source platform for hardware embedded security research", Constructive Side-Channel Analysis and Secure Design: 5th International Workshop, COSADE 2014, pp.243~260 (2014), Springer International Publishing

관련 논문AI추천

비프로파일링 기반 전력 분석의 성능 향상을 위한 오토인코더 기반 잡음 제거 기술권동근, 김희석, 진성현, 홍석희한국정보보호학회 · 정보보호학회논문지2019 · 제29권 제3호축소 마스킹에 효율적인 딥러닝 기반 부채널 분석 방안김주환, 오성빈, 조병모, 한동국한국정보보호학회 · 정보보호학회논문지2025 · 제35권 제5호부채널 분석을 이용한 딥러닝 네트워크 신규 내부 비밀정보 복원 방법 연구김희석, 박수진, 이주헌한국정보보호학회 · 정보보호학회논문지2022 · 제32권 제5호경량 딥러닝 가속기를 위한 희소 행렬 압축 기법 및 하드웨어 설계김선희, 신동엽, 임용석(사)디지털산업정보학회 · (사)디지털산업정보학회 논문지2021 · 제17권 제4호HW 구현 대칭키 암호에 대한 범용적 딥러닝 기반 프로파일링 부채널 분석 방안김주환, 박혜진, 오충연, 최기훈, 한동국한국정보보호학회 · 정보보호학회논문지2025 · 제35권 제1호효과적인 딥러닝 기반 비프로파일링 부채널 분석 모델 설계방안김주환, 심보연, 임한섭, 한동국, 한재승한국정보보호학회 · 정보보호학회논문지2020 · 제30권 제6호

이 간행물의 다른 논문 (14건)

리눅스 의사난수발생기의 구조 변화 분석유태일, 노동영pp. 365-378배터리 소모 공격에 대응하는 저전력 웨이크업 리시버의 적응형 파워 세이빙 메커니즘윤성원, 이일구, 김소연pp. 393-401코드패치 및 하이브리드 분석 환경을 활용한 악성코드 데이터셋 추출 프레임워크 설계최기상, 최상훈, 박기웅pp. 403-416그래프 기반 이기종 위협정보 분석기술 연구이태진, 이예은pp. 417-430GPS 스푸핑 공격 취약점 분석 및 실증: 상용 드론을 대상으로김민재, 이경률, 윤진서pp. 431-437
원문 보기