Single-Trace Attack Using One-Shot Learning With Siamese Network in Non-Profiled Setting
Recently, many studies have shown that using deep learning for side-channel attacks offers several advantages, including simplification of the attack phase and target breaking, even in protected implementations, while presenting outstanding attack performance. Power and electromagnetic analysis, whi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9791229/ |
| _version_ | 1828151085213155328 |
|---|---|
| author | Nayeon Lee Seokhie Hong Heeseok Kim |
| author_facet | Nayeon Lee Seokhie Hong Heeseok Kim |
| author_sort | Nayeon Lee |
| collection | DOAJ |
| description | Recently, many studies have shown that using deep learning for side-channel attacks offers several advantages, including simplification of the attack phase and target breaking, even in protected implementations, while presenting outstanding attack performance. Power and electromagnetic analysis, which is known as the most robust attack, can be classified into profiling and non-profiling attacks. In the real world, a non-profiling attack is more ideal than a profiling attack. In particular, studies on non-profiling attacks using deep learning for asymmetric cryptosystems are rare and have shortcomings, such as a long analysis time. In this paper, we propose a novel non-profiling attack method for asymmetric cryptosystems that requires only a single trace and a reasonably short attack time to recover a full private key, overcoming the limitations of previous studies. The proposed method applies one-shot learning with a convolutional Siamese network, which is used for the first time in side-channel attacks. Thus, our proposed method can leak private keys used in a protected public-key cryptosystem with up to 100% accuracy with only one single trace in a non-profiled setting. |
| first_indexed | 2024-04-11T21:52:54Z |
| format | Article |
| id | doaj.art-1b2716b158a54192bad0bd4050fdc93a |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T21:52:54Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-1b2716b158a54192bad0bd4050fdc93a2022-12-22T04:01:12ZengIEEEIEEE Access2169-35362022-01-0110607786078910.1109/ACCESS.2022.31807429791229Single-Trace Attack Using One-Shot Learning With Siamese Network in Non-Profiled SettingNayeon Lee0https://orcid.org/0000-0002-1487-8143Seokhie Hong1https://orcid.org/0000-0001-7506-4023Heeseok Kim2https://orcid.org/0000-0001-8137-4810Institute of Cyber Security and Privacy (ICSP), Korea University, Seoul, Republic of KoreaInstitute of Cyber Security and Privacy (ICSP), Korea University, Seoul, Republic of KoreaDepartment of AI Cyber Security, College of Science and Technology, Korea University, Sejong, Republic of KoreaRecently, many studies have shown that using deep learning for side-channel attacks offers several advantages, including simplification of the attack phase and target breaking, even in protected implementations, while presenting outstanding attack performance. Power and electromagnetic analysis, which is known as the most robust attack, can be classified into profiling and non-profiling attacks. In the real world, a non-profiling attack is more ideal than a profiling attack. In particular, studies on non-profiling attacks using deep learning for asymmetric cryptosystems are rare and have shortcomings, such as a long analysis time. In this paper, we propose a novel non-profiling attack method for asymmetric cryptosystems that requires only a single trace and a reasonably short attack time to recover a full private key, overcoming the limitations of previous studies. The proposed method applies one-shot learning with a convolutional Siamese network, which is used for the first time in side-channel attacks. Thus, our proposed method can leak private keys used in a protected public-key cryptosystem with up to 100% accuracy with only one single trace in a non-profiled setting.https://ieeexplore.ieee.org/document/9791229/Deep learningECCMontgomery laddernon-profiling attackone-shot learningside channel attack |
| spellingShingle | Nayeon Lee Seokhie Hong Heeseok Kim Single-Trace Attack Using One-Shot Learning With Siamese Network in Non-Profiled Setting IEEE Access Deep learning ECC Montgomery ladder non-profiling attack one-shot learning side channel attack |
| title | Single-Trace Attack Using One-Shot Learning With Siamese Network in Non-Profiled Setting |
| title_full | Single-Trace Attack Using One-Shot Learning With Siamese Network in Non-Profiled Setting |
| title_fullStr | Single-Trace Attack Using One-Shot Learning With Siamese Network in Non-Profiled Setting |
| title_full_unstemmed | Single-Trace Attack Using One-Shot Learning With Siamese Network in Non-Profiled Setting |
| title_short | Single-Trace Attack Using One-Shot Learning With Siamese Network in Non-Profiled Setting |
| title_sort | single trace attack using one shot learning with siamese network in non profiled setting |
| topic | Deep learning ECC Montgomery ladder non-profiling attack one-shot learning side channel attack |
| url | https://ieeexplore.ieee.org/document/9791229/ |
| work_keys_str_mv | AT nayeonlee singletraceattackusingoneshotlearningwithsiamesenetworkinnonprofiledsetting AT seokhiehong singletraceattackusingoneshotlearningwithsiamesenetworkinnonprofiledsetting AT heeseokkim singletraceattackusingoneshotlearningwithsiamesenetworkinnonprofiledsetting |