Akira KITAYAMA Goichi ONO Hiroaki ITO
Edge devices with strict safety and reliability requirements, such as autonomous driving cars, industrial robots, and drones, necessitate software verification on such devices before operation. The human cost and time required for this analysis constitute a barrier in the cycle of software development and updating. In particular, the final verification at the edge device should at least strictly confirm that the updated software is not degraded from the current it. Since the edge device does not have the correct data, it is necessary for a human to judge whether the difference between the updated software and the operating it is due to degradation or improvement. Therefore, this verification is very costly. This paper proposes a novel automated method for efficient verification on edge devices of an object detection AI, which has found practical use in various applications. In the proposed method, a target object existence detector (TOED) (a simple binary classifier) judges whether an object in the recognition target class exists in the region of a prediction difference between the AI’s operating and updated versions. Using the results of this TOED judgement and the predicted difference, an automated verification system for the updated AI was constructed. TOED was designed as a simple binary classifier with four convolutional layers, and the accuracy of object existence judgment was evaluated for the difference between the predictions of the YOLOv5 L and X models using the Cityscapes dataset. The results showed judgement with more than 99.5% accuracy and 8.6% over detection, thus indicating that a verification system adopting this method would be more efficient than simple analysis of the prediction differences.
Daxiu ZHANG Xianwei LI Bo WEI Yukun SHI
With the increase of the number of Mobile User Equipments (MUEs), numerous tasks that with high requirements of resources are generated. However, the MUEs have limited computational resources, computing power and storage space. In this paper, a joint coverage constrained task offloading and resource allocation method based on deep reinforcement learning is proposed. The aim is offloading the tasks that cannot be processed locally to the edge servers to alleviate the conflict between the resource constraints of MUEs and the high performance task processing. The studied problem considers the dynamic variability and complexity of the system model, coverage, offloading decisions, communication relationships and resource constraints. An entropy weight method is used to optimize the resource allocation process and balance the energy consumption and execution time. The results of the study show that the number of tasks and MUEs affects the execution time and energy consumption of the task offloading and resource allocation processes in the interest of the service provider, and enhances the user experience.
Nihad A. A. ELHAG Liang LIU Ping WEI Hongshu LIAO Lin GAO
The concept of dual function radar-communication (DFRC) provides solution to the problem of spectrum scarcity. This paper examines a multiple-input multiple-output (MIMO) DFRC system with the assistance of a reconfigurable intelligent surface (RIS). The system is capable of sensing multiple spatial directions while serving multiple users via orthogonal frequency division multiplexing (OFDM). The objective of this study is to design the radiated waveforms and receive filters utilized by both the radar and users. The mutual information (MI) is used as an objective function, on average transmit power, for multiple targets while adhering to constraints on power leakage in specific directions and maintaining each user’s error rate. To address this problem, we propose an optimal solution based on a computational genetic algorithm (GA) using bisection method. The performance of the solution is demonstrated by numerical examples and it is shown that, our proposed algorithm can achieve optimum MI and the use of RIS with the MIMO DFRC system improving the system performance.
Ryoto KOIZUMI Xiaoyan WANG Masahiro UMEHIRA Ran SUN Shigeki TAKEDA
In recent years, high-resolution 77 GHz band automotive radar, which is indispensable for autonomous driving, has been extensively investigated. In the future, as vehicle-mounted CS (chirp sequence) radars become more and more popular, intensive inter-radar wideband interference will become a serious problem, which results in undesired miss detection of targets. To address this problem, learning-based wideband interference mitigation method has been proposed, and its feasibility has been validated by simulations. In this paper, firstly we evaluated the trade-off between interference mitigation performance and model training time of the learning-based interference mitigation method in a simulation environment. Secondly, we conducted extensive inter-radar interference experiments by using multiple 77 GHz MIMO (Multiple-Input and Multiple-output) CS radars and collected real-world interference data. Finally, we compared the performance of learning-based interference mitigation method with existing algorithm-based methods by real experimental data in terms of SINR (signal to interference plus noise ratio) and MAPE (mean absolute percentage error).
We consider Feistel ciphers instantiated with tweakable block ciphers (TBCs) and ideal ciphers (ICs). The indistinguishability security of the TBC-based Feistel cipher is known, and the indifferentiability security of the IC-based Feistel cipher is also known, where independently keyed TBCs and independent ICs are assumed. In this paper, we analyze the security of a single-keyed TBC-based Feistel cipher and a single IC-based Feistel cipher. We characterize the security depending on the number of rounds. More precisely, we cover the case of contracting Feistel ciphers that have d ≥ 2 lines, and the results on Feistel ciphers are obtained as a special case by setting d = 2. Our indistinguishability security analysis shows that it is provably secure with d + 1 rounds. Our indifferentiability result shows that, regardless of the number of rounds, it cannot be secure. Our attacks are a type of a slide attack, and we consider a structure that uses a round constant, which is a well-known countermeasure against slide attacks. We show an indifferentiability attack for the case d = 2 and 3 rounds.
Dongjae LEE Deukjo HONG Jaechul SUNG Seokhie HONG
In this study, we focus on evaluating the false-positive probability of the Demirci-Selçuk meet-in-the-middle attack, particularly within the context of configuring precomputed tables with multisets. During the attack, the adversary effectively reduces the size of the key space by filtering out the wrong keys, subsequently recovering the master key from the reduced key space. The false-positive probability is defined as the probability that a wrong key will pass through the filtering process. Due to its direct impact on the post-filtering key space size, the false-positive probability is an important factor that influences the complexity and feasibility of the attack. However, despite its significance, the false-positive probability of the multiset-based Demirci-Selçuk meet-in-the-middle attack has not been thoroughly discussed, to the best of our knowledge. We generalize the Demirci-Selçuk meet-in-the-middle attack and present a sophisticated method for accurately calculating the false-positive probability. We validate our methodology through toy experiments, demonstrating its high precision. Additionally, we propose a method to optimize an attack by determining the optimal format of precomputed data, which requires the precise false-positive probability. Applying our approach to previous attacks on AES and ARIA, we have achieved modest improvements. Specifically, we enhance the memory complexity and time complexity of the offline phase of previous attacks on 7-round AES-128/192/256, 7-round ARIA-192/256, and 8-round ARIA-256 by factors ranging from 20.56 to 23. Additionally, we have improved the overall time complexity of attacks on 7-round ARIA-192/256 by factors of 20.13 and 20.42, respectively.
Changhui CHEN Haibin KAN Jie PENG Li WANG
Permutation polynomials have been studied for a long time and have important applications in cryptography, coding theory and combinatorial designs. In this paper, by means of the multivariate method and the resultant, we propose four new classes of permutation quadrinomials over 𝔽q3, where q is a prime power. We also show that they are not quasi-multiplicative equivalent to known ones. Moreover, we compare their differential uniformity with that of some known classes of permutation trinomials for some small q.
Nobuyuki TAKEUCHI Kosei SAKAMOTO Takuro SHIRAYA Takanori ISOBE
At CT-RSA 2022, Bossert et al. proposed Pholkos family, an efficient large-state tweakable block cipher. In order to evaluate the security of differential attacks on Pholkos, they obtained the lower bounds for the number of active S-boxes for Pholkos using MILP (Mixed Integer Linear Programming) tools. Based on it, they claimed that Pholkos family is secure against differential attacks. However, they only gave rough security bounds in both of related-tweak and related-tweakey settings. To be more precise, they estimated the lower bounds of the number of active S-boxes for relatively-large number of steps by just summing those in the small number of steps. In this paper, we utilize efficient search methods based on MILP to obtain tighter lower bounds for the number of active S-boxes in a larger number of steps. For the first time, we derive the exact minimum number of active S-boxes of each variant up to the steps where the security against differential attacks can be ensured in related-tweak and related-tweakey settings. Our results indicate that Pholkos-256-128/256-256/512/1024 is secure after 4/5/3/4 steps in the related-tweak setting, and after 5/6/3/4 steps in the related-tweakey setting, respectively. Our results enable reducing the required number of steps to be secure against differential attacks of Pholkos-256-256 in related-tweak setting, and Pholkos-256-128/256 and Pholkos-1024 in the related-tweakey setting by one step, respectively.
Shion UTSUMI Kosei SAKAMOTO Takanori ISOBE
Lightweight block ciphers have gained attention in recent years due to the increasing demand for sensor nodes, RFID tags, and various applications. In such a situation, lightweight block ciphers Piccolo and TWINE have been proposed. Both Piccolo and TWINE are designed based on the Generalized Feistel Structure. However, it is crucial to address the potential vulnerability of these structures to the impossible differential attack. Therefore, detailed security evaluations against this attack are essential. This paper focuses on conducting bit-level evaluations of Piccolo and TWINE against related-key impossible differential attacks by leveraging SAT-aided approaches. We search for the longest distinguishers under the condition that the Hamming weight of the active bits of the input, which includes plaintext and master key differences, and output differences is set to 1, respectively. Additionally, for Tweakable TWINE, we search for the longest distinguishers under the related-tweak and related-tweak-key settings. The result for Piccolo with a 128-bit key, we identify the longest 16-round distinguishers for the first time. In addition, we also demonstrate the ability to extend these distinguishers to 17 rounds by taking into account the cancellation of the round key and plaintext difference. Regarding evaluations of TWINE with a 128-bit key, we search for the first time and reveal the distinguishers up to 19 rounds. For the search for Tweakable TWINE, we evaluate under the related-tweak-key setting for the first time and reveal the distinguishers up to 18 rounds for 80-bit key and 19 rounds for 128-bit key.
Homomorphic encryption (HE) is a promising approach for privacy-preserving applications, enabling a third party to assess functions on encrypted data. However, problems persist in implementing privacy-preserving applications through HE, including 1) long function evaluation latency and 2) limited HE primitives only allowing us to perform additions and multiplications. A homomorphic lookup-table (LUT) method has emerged to solve the above problems and enhance function evaluation efficiency. By leveraging homomorphic LUTs, intricate operations can be substituted. Previously proposed LUTs use bit-wise HE, such as TFHE, to evaluate single-input functions. However, the latency increases with the bit-length of the function’s input(s) and output. Additionally, an efficient implementation of multi-input functions remains an open question. This paper proposes a novel LUT-based privacy-preserving function evaluation method to handle multi-input functions while reducing the latency by adopting word-wise HE. Our optimization strategy adjusts table sizes to minimize the latency while preserving function output accuracy, especially for common machine-learning functions. Through our experimental evaluation utilizing the BFV scheme of the Microsoft SEAL library, we confirmed the runtime of arbitrary functions whose LUTs consist of all input-output combinations represented by given input bits: 1) single-input 12-bit functions in 0.14 s, 2) single-input 18-bit functions in 2.53 s, 3) two-input 6-bit functions in 0.17 s, and 4) three-input 4-bit functions in 0.20 s, employing four threads. Besides, we confirmed that our proposed table size optimization strategy worked well, achieving 1.2 times speed up with the same absolute error of order of magnitude of -4 (a × 10-4 where 1/$\sqrt{10}$ ≤ a < $\sqrt{10})$ for Swish and 1.9 times speed up for ReLU while decreasing the absolute error from order -2 to -4 compared to the baseline, i.e., polynomial approximation.
Ryuta TAMURA Yuichi TAKANO Ryuhei MIYASHIRO
We study the mixed-integer optimization (MIO) approach to feature subset selection in nonlinear kernel support vector machines (SVMs) for binary classification. To measure the performance of subset selection, we use the distance between two classes (DBTC) in a high-dimensional feature space based on the Gaussian kernel function. However, DBTC to be maximized as an objective function is nonlinear, nonconvex and nonconcave. Despite the difficulty of linearizing such a nonlinear function in general, our major contribution is to propose a mixed-integer linear optimization (MILO) formulation to maximize DBTC for feature subset selection, and this MILO problem can be solved to optimality using optimization software. We also derive a reduced version of the MILO problem to accelerate our MILO computations. Experimental results show good computational efficiency for our MILO formulation with the reduced problem. Moreover, our method can often outperform the linear-SVM-based MILO formulation and recursive feature elimination in prediction performance, especially when there are relatively few data instances.
Riaz-ul-haque MIAN Tomoki NAKAMURA Masuo KAJIYAMA Makoto EIKI Michihiro SHINTANI
Wafer-level performance prediction techniques have been increasingly gaining attention in production LSI testing due to their ability to reduce measurement costs without compromising test quality. Despite the availability of several efficient methods, the site-to-site variation commonly observed in multi-site testing for radio frequency circuits remains inadequately addressed. In this manuscript, we propose a wafer-level performance prediction approach for multi-site testing that takes into account the site-to-site variation. Our proposed method is built on the Gaussian process, a widely utilized wafer-level spatial correlation modeling technique, and enhances prediction accuracy by extending hierarchical modeling to leverage the test site information test engineers provide. Additionally, we propose a test-site sampling method that maximizes cost reduction while maintaining sufficient estimation accuracy. Our experimental results, which employ industrial production test data, demonstrate that our proposed method can decrease the estimation error to 1/19 of that a conventional method achieves. Furthermore, our sampling method can reduce the required measurements by 97% while ensuring satisfactory estimation accuracy.
Yusaku HIRAI Toshimasa MATSUOKA Takatsugu KAMATA Sadahiro TANI Takao ONOYE
This paper presents a multi-channel biomedical sensor system with system-level chopping and stochastic analog-to-digital (A/D) conversion techniques. The system-level chopping technique extends the input-signal bandwidth and reduces the interchannel crosstalk caused by multiplexing. The system-level chopping can replace an analog low-pass filter (LPF) with a digital filter and can reduce its area occupation. The stochastic A/D conversion technique realizes power-efficient resolution enhancement. A novel auto-calibration technique is also proposed for the stochastic A/D conversion technique. The proposed system includes a prototype analog front-end (AFE) IC fabricated using a 130 nm CMOS process. The fabricated AFE IC improved its interchannel crosstalk by 40 dB compared with the conventional analog chopping architecture. The AFE IC achieved SNDR of 62.9 dB at a sampling rate of 31.25 kSps while consuming 9.6 μW from a 1.2 V power supply. The proposed resolution enhancement technique improved the measured SNDR by 4.5 dB.
Zhimin SHAO Chunxiu LIU Cong WANG Longtan LI Yimin LIU Zaiyan ZHOU
Data resource sharing can guarantee the reliable and safe operation of distribution power grid. However, it faces the challenges of low security and high delay in the sharing process. Consortium blockchain can ensure the security and efficiency of data resource sharing, but it still faces problems such as arbitrary master node selection and high consensus delay. In this paper, we propose an improved practical Byzantine fault tolerance (PBFT) consensus algorithm based on intelligent consensus node selection to realize high-security and real-time data resource sharing for distribution power grid. Firstly, a blockchain-based data resource sharing model is constructed to realize secure data resource storage by combining the consortium blockchain and interplanetary file system (IPFS). Then, the improved PBFT consensus algorithm is proposed to optimize the consensus node selection based on the upper confidence bound of node performance. It prevents Byzantine nodes from participating in the consensus process, reduces the consensus delay, and improves the security of data resource sharing. The simulation results verify the effectiveness of the proposed algorithm.
Ryohei KANKE Masanobu TAKAHASHI
Amodal Instance Segmentation (AIS) aims to segment the regions of both visible and invisible parts of overlapping objects. The mainstream Mask R-CNN-based methods are unsuitable for thin objects with large overlaps because of their object proposal features with bounding boxes for three reasons. First, capturing the entire shapes of overlapping thin objects is difficult. Second, the bounding boxes of close objects are almost identical. Third, a bounding box contains many objects in most cases. In this paper, we propose a box-free AIS method, Seed-to-Mask, for thin objects with large overlaps. The method specifies a target object using a seed and iteratively extends the segmented region. We have achieved better performance in experiments on artificial data consisting only of thin objects.
Xueying WANG Yuan HUANG Xin LONG Ziji MA
In recent years, the increasing complexity of deep network structures has hindered their application in small resource constrained hardware. Therefore, we urgently need to compress and accelerate deep network models. Channel pruning is an effective method to compress deep neural networks. However, most existing channel pruning methods are prone to falling into local optima. In this paper, we propose a channel pruning method via Improved Grey Wolf Optimizer Pruner which called IGWO-Pruner to prune redundant channels of convolutional neural networks. It identifies pruning ratio of each layer by using Improved Grey Wolf algorithm, and then fine-tuning the new pruned network model. In experimental section, we evaluate the proposed method in CIFAR datasets and ILSVRC-2012 with several classical networks, including VGGNet, GoogLeNet and ResNet-18/34/56/152, and experimental results demonstrate the proposed method is able to prune a large number of redundant channels and parameters with rare performance loss.
The prediction of peak power load is a critical factor directly impacting the stability of power supply, characterized significantly by its time series nature and intricate ties to the seasonal patterns in electricity usage. Despite its crucial importance, the current landscape of power peak load forecasting remains a multifaceted challenge in the field. This study aims to contribute to this domain by proposing a method that leverages a combination of three primary models - the GRU model, self-attention mechanism, and Transformer mechanism - to forecast peak power load. To contextualize this research within the ongoing discourse, it’s essential to consider the evolving methodologies and advancements in power peak load forecasting. By delving into additional references addressing the complexities and current state of the power peak load forecasting problem, this study aims to build upon the existing knowledge base and offer insights into contemporary challenges and strategies adopted within the field. Data preprocessing in this study involves comprehensive cleaning, standardization, and the design of relevant functions to ensure robustness in the predictive modeling process. Additionally, recognizing the necessity to capture temporal changes effectively, this research incorporates features such as “Weekly Moving Average” and “Monthly Moving Average” into the dataset. To evaluate the proposed methodologies comprehensively, this study conducts comparative analyses with established models such as LSTM, Self-attention network, Transformer, ARIMA, and SVR. The outcomes reveal that the models proposed in this study exhibit superior predictive performance compared to these established models, showcasing their effectiveness in accurately forecasting electricity consumption. The significance of this research lies in two primary contributions. Firstly, it introduces an innovative prediction method combining the GRU model, self-attention mechanism, and Transformer mechanism, aligning with the contemporary evolution of predictive modeling techniques in the field. Secondly, it introduces and emphasizes the utility of “Weekly Moving Average” and “Monthly Moving Average” methodologies, crucial in effectively capturing and interpreting seasonal variations within the dataset. By incorporating these features, this study enhances the model’s ability to account for seasonal influencing factors, thereby significantly improving the accuracy of peak power load forecasting. This contribution aligns with the ongoing efforts to refine forecasting methodologies and addresses the pertinent challenges within power peak load forecasting.
Beibei LI Xun RAN Yiran LIU Wensheng LI Qingling DUAN
Fish skin color detection plays a critical role in aquaculture. However, challenges arise from image color cast and the limited dataset, impacting the accuracy of the skin color detection process. To address these issues, we proposed a novel fish skin color detection method, termed VH-YOLOv5s. Specifically, we constructed a dataset for fish skin color detection to tackle the limitation posed by the scarcity of available datasets. Additionally, we proposed a Variance Gray World Algorithm (VGWA) to correct the image color cast. Moreover, the designed Hybrid Spatial Pyramid Pooling (HSPP) module effectively performs multi-scale feature fusion, thereby enhancing the feature representation capability. Extensive experiments have demonstrated that VH-YOLOv5s achieves excellent detection results on the Plectropomus leopardus skin color dataset, with a precision of 91.7%, recall of 90.1%, mAP@0.5 of 95.2%, and mAP@0.5:0.95 of 57.5%. When compared to other models such as Centernet, AutoAssign, and YOLOX-s, VH-YOLOv5s exhibits superior detection performance, surpassing them by 2.5%, 1.8%, and 1.7%, respectively. Furthermore, our model can be deployed directly on mobile phones, making it highly suitable for practical applications.
Xiao’an BAO Shifan ZHOU Biao WU Xiaomei TU Yuting JIN Qingqi ZHANG Na ZHANG
With the popularization of software defined networks, switch migration as an important network management strategy has attracted increasing attention. Most existing switch migration strategies only consider local conditions and simple load thresholds, without fully considering the overall optimization and dynamics of the network. Therefore, this article proposes a switch migration algorithm based on global optimization. This algorithm adds a load prediction module to the migration model, determines the migration controller, and uses an improved whale optimization algorithm to determine the target controller and its surrounding controller set. Based on the load status of the controller and the traffic priority of the switch to be migrated, the optimal migration switch set is determined. The experimental results show that compared to existing schemes, the algorithm proposed in this paper improves the average flow processing efficiency by 15% to 40%, reduces switch migration times, and enhances the security of the controller.
Hiroki NAKANO Daiki CHIBA Takashi KOIDE Naoki FUKUSHI Takeshi YAGI Takeo HARIU Katsunari YOSHIOKA Tsutomu MATSUMOTO
The increase in phishing attacks through email and short message service (SMS) has shown no signs of deceleration. The first thing we need to do to combat the ever-increasing number of phishing attacks is to collect and characterize more phishing cases that reach end users. Without understanding these characteristics, anti-phishing countermeasures cannot evolve. In this study, we propose an approach using Twitter as a new observation point to immediately collect and characterize phishing cases via e-mail and SMS that evade countermeasures and reach users. Specifically, we propose CrowdCanary, a system capable of structurally and accurately extracting phishing information (e.g., URLs and domains) from tweets about phishing by users who have actually discovered or encountered it. In our three months of live operation, CrowdCanary identified 35,432 phishing URLs out of 38,935 phishing reports. We confirmed that 31,960 (90.2%) of these phishing URLs were later detected by the anti-virus engine, demonstrating that CrowdCanary is superior to existing systems in both accuracy and volume of threat extraction. We also analyzed users who shared phishing threats by utilizing the extracted phishing URLs and categorized them into two distinct groups - namely, experts and non-experts. As a result, we found that CrowdCanary could collect information that is specifically included in non-expert reports, such as information shared only by the company brand name in the tweet, information about phishing attacks that we find only in the image of the tweet, and information about the landing page before the redirect. Furthermore, we conducted a detailed analysis of the collected information on phishing sites and discovered that certain biases exist in the domain names and hosting servers of phishing sites, revealing new characteristics useful for unknown phishing site detection.