Yuta Fukuda

Dr. Yuta Fukuda


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 August 2023 in IEEE Access
Verified
Journal Article
Open access
YFYuta Fukuda
Yuta Fukuda
KYKota Yoshida
Kota Yoshida
TFTakeshi Fujino
Takeshi Fujino
Adversarial examples (AEs) are typical model evasion attacks and security threats in deep neural networks (DNNs). One of the countermeasures is adversarial training (AT), and it trains DNNs by using a training dataset containing AEs to achieve robustness against AEs. On the other hand, the robustness obtained by AT greatly decreases when its parameters are quantized from a 32-bit float into an 8-bit integer to execute DNNs on edge devices with restricted hardware resources. Preliminary experiments in this study show that robustness is reduced by the fine-tuning process, in which a quantized model is trained with clean samples to reduce quantization errors. We propose quantization-aware adversarial training (QAAT) to address this problem, optimizing DNNs by conducting AT in quantization flow. In this study, we constructed a QAAT model using Vitis-AI provided by Xilinx. We implemented the QAAT model on the evaluation board ZCU104, equipped with Zynq UltraScale+, and demonstrate the robustness against AEs.

27 March 2023 in Journal of Cryptographic Engineering
Verified
Journal Article
Open access
PDF file
KKKunihiro Kuroda
Kunihiro Kuroda
YFYuta Fukuda
Yuta Fukuda
KYKota Yoshida
Kota Yoshida
TFTakeshi Fujino
Takeshi Fujino
Deep-learning side-channel attacks, applying deep neural networks to side-channel attacks, are known that can easily attack some existing side-channel attack countermeasures such as masking and random jitter. While there have been many studies on profiled deep-learning side-channel attacks, a new approach that involves applying deep learning to non-profiled attacks was proposed in 2018. In our study, we investigate the structure of multi-layer perceptrons and points of interest for non-profiled deep-learning side-channel attacks using the ANSSI database with a masking countermeasure. The results of investigations indicate that it is better to use a simple network model, apply regularization to prevent over-fitting, and select a wide range of power traces that contain side-channel information as the points of interest. We also implemented AES-128 software implementation protected with the Rotating Sboxes Masking countermeasure, which has never been attacked by non-profiled deep-learning side-channel attacks, on the Xmega128 microcontroller and carried out non-profiled deep-learning side-channel attacks against it. Non-profiled deep-learning side-channel attacks successfully recovered all partial keys while the conventional power analysis could not. The attack results also showed that the least significant bit is the adequate selection for successful non-profiled deep-learning side-channel attacks, but the best labeling method may vary depending on the implementation of the countermeasure algorithm. We conducted two experimental analyses to clarify that deep-learning side-channel attacks learn mask values used in the masking countermeasure. One is the gradient visualization used in previous studies, and the other is a new analysis method using partial removal of power traces.

1 January 2022 in IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Verified
Journal Article
Closed access
PDF file
YFYuta Fukuda
Yuta Fukuda
KYKota Yoshida
Kota Yoshida
HHHisashi Hashimoto
Hisashi Hashimoto
KKKunihiro Kuroda
Kunihiro Kuroda
TFTakeshi Fujino
Takeshi Fujino
Deep learning side-channel attacks (DL-SCAs) have been actively studied in recent years. In the DL-SCAs, deep neural networks (DNNs) are trained to predict the internal states of the cryptographic operation from the side-channel information such as power traces. It is important to select suitable DNN output labels expressing an internal states for successful DL-SCAs. We focus on the multi-label method proposed by Zhang et al. for the hardware-implemented advanced encryption standard (AES). They used the power traces supplied from the AES-HD public dataset, and reported to reveal a single key byte on conditions in which the target key was the same as the key used for DNN training (profiling key). In this paper, we discuss an improvement for revealing all the 16 key bytes in practical conditions in which the target key is different from the profiling key. We prepare hardware-implemented AES without SCA countermeasures on ASIC for the experimental environment. First, our experimental results show that the DNN using multi-label does not learn side-channel leakage sufficiently from the power traces acquired with only one key. Second, we report that DNN using multi-label learns the most of side-channel leakage by using three kinds of profiling keys, and all the 16 target key bytes are successfully revealed even if the target key is different from the profiling keys. Finally, we applied the proposed method, DL-SCA using multi-label and three profiling keys against hardware-implemented AES with rotating S-boxes masking (RSM) countermeasures. The experimental result shows that all the 16 key bytes are successfully revealed by using only 2,000 attack traces. We also studied the reasons for the high performance of the proposed method against RSM countermeasures and found that the information from the weak bits is effectively exploited.


1 March 2025 in IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Verified
Journal Article
Open access
PDF file
YFYuta Fukuda
Yuta Fukuda
KYKota Yoshida
Kota Yoshida
TFTakeshi Fujino
Takeshi Fujino
Side-channel attacks (SCAs) using deep learning techniques have been mainly reported as profiled attacks, but in TCHES 2019, differential deep learning analysis (DDLA) was proposed by Timon as a non-profiled attack. In this attack method, deep learning models for all candidate keys are trained, and the key corresponding to the most suitable learning metrics such as loss and accuracy is assumed to be the correct key. Timon focused on a single bit (least significant bit (LSB) or most significant bit (MSB)) of the intermediate value during the operation of the cryptographic circuit and successfully revealed the correct key against the software implementation of the advanced encryption standard (AES). However, when we applied this method to our hardware implementation, we could not reveal all partial keys due to the existence of registers whose Hamming distance (HD) leakage is difficult to observe. In this paper, we propose a multi-bit DDLA that focuses on all bits to solve this problem. When a DDLA was performed on the hardware implemented AES without SCA countermeasures, the HD-ID labels, which had been used as a conventional profiled type DL-SCA method focusing on 8 bits, cannot reveal the 0, 4, 8, and 12th byte keys, but the proposed multi-bit method succeeds in revealing all key bytes. On the other hand, compared to correlated power analysis (CPA) which is a typical non-profiled attack that does not use deep learning, the number of waveforms required to reveal all keys is 1.6 times higher, so the DDLA with our proposed method is not so useful to the target without SCA countermeasures. Thus, we also evaluated the proposed method against FPGA-implemented RSM-AES and WDDL-AES, which have some resistance to SCA, and successfully revealed all keys against RSM and WDDL with 100,000 and 50,000 waveforms, respectively. This is a significant improvement over conventional CPA, which reveals less than half of the key bytes despite using twice as many waveforms as the proposed method. These results suggest that multi-bit DDLA is effective on non-profiled attacks against hardware-implemented AES circuit with SCA countermeasures.

1 March 2025 in IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Verified
Journal Article
Open access
PDF file
YFYuta Fukuda
Yuta Fukuda
KYKota Yoshida
Kota Yoshida
TFTakeshi Fujino
Takeshi Fujino
Differential deep learning analysis (DDLA) was proposed as a side-channel attack (SCA) with deep learning techniques in non-profiled scenarios at TCHES 2019. In the proposed DDLA, the adversary sets the LSB or MSB of the intermediate value in the encryption process assumed for the key candidates as the ground-truth label and trains a deep neural network (DNN) with power traces as an input. The adversary also observes metrics such as loss and accuracy during DNN training and estimates that the key corresponding to the best-fitting DNN is correct. One of the disadvantages of DDLA is the heavy computation time for the DNN models because the number of required models is the as same as the number of key candidates, which is 256 in the case of AES. Therefore 4096 DNNs are required for revealing keys of 16 bytes. Furthermore, the DNN models have to be trained again if the adversary changes a ground-truth label function from LSB to other labels such as MSB or HW. We propose a new deep-learning-based SCA in a non-profiled scenario to solve these problems. Our core idea is to extract feature of the leakage waveform using DNN. The adversary reveals the correct keys by conducting cluster analysis using the feature vectors extracted from power traces using DNN. We named this method as CA-SCA (cluster-analysis-based side-channel attacks), it is advantageous that only one DNN needs to be trained to reveal all key bytes. In addition, once the DNN is trained, multiple label functions can be tested without the additional cost of training DNNs. We provide four case studies of attacking against AES, including two software implementations and two hardware implementations. Our attacks against software implementations provide methods using a concatenated dataset that efficiently train the DNN. Also, our attack on the hardware implementation introduces multitask learning to exploit the Hamming distance leakage model. The results show that the proposed method requires fewer waveforms to reveal all key bytes than DDLA owing to the efficient learning performance on the above methods. Comparing the computation time to process the same number of waveforms, the proposed method requires only about 1/75 and 1/25 of the time when attacking software and hardware implementations, respectively, due to the significant reduction in the number of training models.