Takeshi Fujino

Dr. Takeshi Fujino


Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
3 October 2024 in Sensors
Verified
Journal Article
Open access
PDF file
TITakahito Ino
Takahito Ino
KYKota Yoshida
Kota Yoshida
HMHiroki Matsutani
Hiroki Matsutani
TFTakeshi Fujino
Takeshi Fujino
In this paper, we introduce a security approach for on-device learning Edge AIs designed to detect abnormal conditions in factory machines. Since Edge AIs are easily accessible by an attacker physically, there are security risks due to physical attacks. In particular, there is a concern that the attacker may tamper with the training data of the on-device learning Edge AIs to degrade the task accuracy. Few risk assessments have been reported. It is important to understand these security risks before considering countermeasures. In this paper, we demonstrate a data poisoning attack against an on-device learning Edge AI. Our attack target is an on-device learning anomaly detection system. The system adopts MEMS accelerometers to measure the vibration of factory machines and detect anomalies. The anomaly detector also adopts a concept drift detection algorithm and multiple models to accommodate multiple normal patterns. For the attack, we used a method in which measurements are tampered with by exposing the MEMS accelerometer to acoustic waves of a specific frequency. The acceleration data falsified by this method were trained on an anomaly detector, and the result was that the abnormal state could not be detected.

28 February 2014 in Journal of Cryptographic Engineering
Verified
Journal Article
Closed access
PDF file
TSTakeshi Sugawara
Takeshi Sugawara
DSDaisuke Suzuki
Daisuke Suzuki
MSMinoru Saeki
Minoru Saeki
MSMitsuru Shiozaki
Mitsuru Shiozaki
TFTakeshi Fujino
Takeshi Fujino

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.

22 February 2012
Verified
Conference Paper
Open access
AHAnh Tuan Hoang
Anh Tuan Hoang
TFTakeshi Fujino
Takeshi Fujino
In current countermeasure design trends against differential power analysis (DPA), security at gate level is required in addition to the security algorithm. Several dual-rail pre-charge logics (DPL) have been proposed to achieve this goal. Designs using ASIC can attain this goal owing to its backend design restrictions on placement and routing. However, implementing these designs on field programmable gate arrays (FPGA) without information leakage is still a problem because of the difficulty involved in the restrictions on placement and routing on FPGA. This paper describes our novel masked dual-rail pre-charged memory approach, called "intra-masking dual-rail memory on LUT," and its implementation on FPGA for tamper-resistant AES. In the proposed design, all unsafe nodes, such as unmasking and masking, and the dual-rail memory and buses are packed into a single LUT. This makes them balanced and independent of the placement and routing tools. The design is independent of the cryptographic algorithm, and hence, it can be applied to available cryptographic standards such as DES or AES as well as future standards. It requires no special placement or route constraints in its implementation. A correlation power analysis (CPA) attack on 1,000,000 traces of AES implementation on FPGA showed that the secret information is well protected against first-order side-channel attacks. Even though the number of LUTs used for memory in this implementation is seven times greater than that of the conventional unprotected single-rail memory table-lookup AES and three times greater than the implementation based on a composite field, it requires a smaller number of LUTs than all other advanced tamper-resistant implementations such as the wave dynamic differential logic, masked dual-rail pre-charge logic, and threshold.

1 January 2015 in Journal of Signal Processing
Verified
Journal Article
Open access
PDF file
KKKyosuke Kageyama
Kyosuke Kageyama
TKTakeshi Kumaki
Takeshi Kumaki
TOTakeshi Ogura
Takeshi Ogura
TFTakeshi Fujino
Takeshi Fujino
The use of digital images has become quite widespread in legal, medical, and private contexts. However, anyone can easily edit or manipulate any digital image on a computer. Thus, an effective method for detecting digital image manipulation is required for retaining authenticity. Image-manipulation detection is applied in investigations of crimes and photographic evidence. In this paper, we describe a method for detecting morphological pattern spectrum-based human-like image manipulation. All conventional techniques, such as metadata and electronic watermarking, cannot consider the same results between an original and rotated original image the same as a human. However, our method can judge whether an original image and rotated original image are the same. In other words, our method judge an image in the same way as the human eye. We determined that this method could detect a manipulated image. And this method can be used for digital image forensics.

14 May 2023 in Sensors
Verified
Journal Article
Open access
PDF file
TOTatsuya Oyama
Tatsuya Oyama
SOShunsuke Okura
Shunsuke Okura
KYKota Yoshida
Kota Yoshida
TFTakeshi Fujino
Takeshi Fujino
A backdoor attack is a type of attack method that induces deep neural network (DNN) misclassification. The adversary who aims to trigger the backdoor attack inputs the image with a specific pattern (the adversarial mark) into the DNN model (backdoor model). In general, the adversary mark is created on the physical object input to an image by capturing a photo. With this conventional method, the success of the backdoor attack is not stable because the size and position change depending on the shooting environment. So far, we have proposed a method of creating an adversarial mark for triggering backdoor attacks by means of a fault injection attack on the mobile industry processor interface (MIPI), which is the image sensor interface. We propose the image tampering model, with which the adversarial mark can be generated in the actual fault injection to create the adversarial mark pattern. Then, the backdoor model was trained with poison data images, which the proposed simulation model created. We conducted a backdoor attack experiment using a backdoor model trained on a dataset containing 5% poison data. The clean data accuracy in normal operation was 91%; nevertheless, the attack success rate with fault injection was 83%.