A backdoor sample attack is an attack that causes a deep neural network to misrecognize data that include a specific trigger because the model has been trained on malicious data that insert triggers into the deep neural network. The deep neural network correctly recognizes data without triggers, but incorrectly recognizes data with triggers. These backdoor attacks have mainly been studied in the image domain; however, defense research in the text domain is insufficient. In this study, we propose a method to defend against textual backdoor samples using a detection model. The proposed method detects a textual backdoor sample by comparing the resulting value of the target model with that of the model trained on the original training data. This method can defend against attacks without access to the entire training data. For the experimental setup, we used the TensorFlow library, and the MR and IMDB datasets were used as the experimental datasets. As a result of the experiment, when 1000 partial training datasets were used to train the detection model, the proposed method could classify the MR and IMDB datasets with detection rates of 79.6% and 83.2%, respectively.

Integrated circuits used in automotive or aerospace applications must have high soft error tolerance. Redundant Flip Flops (FFs) are effective to improve the soft error tolerance. However, these countermeasures have large performance overheads and can be excessive for terrestrial applications. This paper proposes two types of radiation-hardened FFs named Primary Latch Transmission gate FF (PLTGFF) and Feed-Back Gate Tri-state Inverter FF (FBTIFF) for terrestrial use. By increasing the critical charge (Qcrit) at weak nodes, soft error tolerance of them were improved with low performance overheads. PLTGFF has the 5% area, 4% delay, and 10% power overheads, while FBTIFF has the 42% area, 10% delay, and 22% power overheads. They were fabricated in a 65 nm bulk process. By α-particle and spallation neutron irradiation tests, the soft error rates are reduced by 25% for PLTGFF and 50% for FBTIFF compared to a standard FF. In the terrestrial environment, the proposed FFs have better trade-offs between reliability and performance than those of multiplexed FFs such as the dual-interlocked storage cell (DICE) with larger overheads than the proposed FFs.

Holography is a three-dimensional (3D) technology that enables natural stereoscopic viewing with deep depth and expected for practical use in the future. Based on the recording process of holography, the electronic data generated through numerical simulation in a computer are called computer-generated holograms (CGHs). Displaying the generated CGH on a spatial light modulator and reconstructing a 3D object by illuminating it with light is called electro-holography. One of the issues in the development of 3DTV using electro-holography is the compression and transmission of a CGH. Because of the data loss caused by compression in a CGH, the quality of the reconstructed image may be affected, unlike normal 2D images. In wireless transmission of a CGH, not only data loss due to compression but also retransmissions and drops of data due to unstable network environments occur. These may degrade the quality of the reconstructed image, cause frame drops, and decrease the frame rate. In this paper, we developed a system for streaming CGH videos for reconstructing 3D objects using electro-holography. CGH videos were generated by merging multiple CGHs into a timeline, and the uncompressed or lossless compressed CGH videos were streamed via a network such as wired and wireless local area networks, a local 5G network, and mobile network. The performance of the network and quality of the CGH videos and reconstructed images were evaluated. Optically reconstructed images were obtained from the uncompressed CGH videos streamed via the networks. It was also confirmed that the required bit rate could be reduced without degrading the quality of the reconstructed image by using lossless compression. In some cases of wireless transmission, even when packet loss or retransmission occurs, there was no degradation in the reconstructed image quality.

The learning with errors (LWE) problem is one of the fundamental problems in cryptography and it has many applications in post-quantum cryptography. There are two variants of the problem, the decisional-LWE problem, and the search-LWE problem. LWE search-to-decision reduction shows that the hardness of the search-LWE problem can be reduced to the hardness of the decisional-LWE problem. The efficiency of the reduction can be regarded as the gap in difficulty between the problems. We initiate a study of quantum search-to-decision reduction for the LWE problem and propose a reduction that satisfies sample-preserving. In sample-preserving reduction, it preserves all parameters even the number of instances. Especially, our quantum reduction invokes the distinguisher only 2 times to solve the search-LWE problem, while classical reductions require a polynomial number of invocations. Furthermore, we give a way to amplify the success probability of the reduction algorithm. Our amplified reduction is incomparable to the classical reduction in terms of sample complexity and query complexity. Our reduction algorithm supports a wide class of error distributions and also provides a search-to-decision reduction for the learning parity with noise problem. In the process of constructing the search-to-decision reduction, we give a quantum Goldreich-Levin theorem over ℤq where q is a prime. In short, this theorem states that, if a hardcore predicate a・s (mod q) can be predicted with probability distinctly greater than (1/q) with respect to a uniformly random a ∈ ℤqn, then it is possible to determine s ∈ ℤqn.

Wingsuit flying search is a meta-heuristic algorithm that effectively searches for optimal solutions by narrowing down the search space iteratively. However, its performance is affected by the balance between exploration and exploitation. We propose a four-layered hierarchical population structure algorithm, multi-layered chaotic wingsuit flying search (MCWFS), to promote such balance in this paper. The proposed algorithm consists of memory, elite, sub-elite, and population layers. Communication between the memory and elite layers enhances exploration ability while maintaining population diversity. The information flow from the population layer to the elite layer ensures effective exploitation. We evaluate the performance of the proposed MCWFS algorithm by conducting comparative experiments on IEEE Congress on Evolutionary Computation (CEC) benchmark functions. Experimental results prove that MCWFS is superior to the original algorithm in terms of solution quality and search performance. Compared with other representative algorithms, MCWFS obtains more competitive results on composite problems and real-world problems.

The globalization of the Integrated Circuit (IC) supply chain has introduced the risk of Hardware Trojan (HT) insertion. We propose an unsupervised Hardware Trojan detection method based on the Enhanced Local Outlier Factor (ELOF) algorithm to detect HT efficiently. This method extracts structural and testability features and employs the scoring mechanism of the ELOF algorithm to emphasize the deviation of suspicious HT nets from clusters. Experimental results on Hardware Trojan libraries show that the method achieves an average prediction accuracy (A) of 97.36%, a True Negative Rate (TNR) of 97.81%, a precision (P) of 40.94%, and an F-measure of 49.28%, all of which outperform the Local Outlier Factor (LOF) algorithm and Cluster-Based Local Outlier Factor (CBLOF) algorithm. Notably, the method exhibits superior performance in terms of True Positive Rate (TPR), reaching 70.86%, indicating its efficiency in identifying HT and reducing false negatives. The results demonstrate that the proposed algorithm and feature combination in the approach can significantly enhance the efficiency of Trojan detection.

This paper develops certified defenses for deep neural network (DNN) based content-based image retrieval (CBIR) against adversarial examples (AXs). Previous works put their effort into certified defense for classification to improve certified robustness, which guarantees that no AX to cause misclassification exists around the sample. Such certified defense, however, could not be applied to CBIR directly because the goals of adversarial attack against classification and CBIR are completely different. To develop the certified defense for CBIR, we first define the new certified robustness of CBIR, which guarantees that no AX that changes the ranking results of CBIR exists around the input images. Then, we propose computationally tractable verification algorithms that verify whether a given feature extraction DNN satisfies the certified robustness of CBIR at given input images. Our proposed verification algorithms are achieved by evaluating the upper and lower bounds of distances between feature representations of perturbed and non-perturbed images in deterministic and probabilistic manners. Finally, we propose robust training methods to obtain feature extraction DNNs that increase the number of inputs that satisfy the certified robustness of CBIR by tightening the upper and lower bounds. We experimentally show that our proposed certified defenses can guarantee robustness deterministically and probabilistically on various datasets.

Federated Learning (FL) facilitates deep learning model training across distributed networks while ensuring data privacy. When deployed on edge devices, network pruning becomes essential due to the constraints of computational resources. However, traditional FL pruning methods face bias issues arising from the varied distribution of local data, which poses a significant challenge. To address this, we propose DDPruneFL, an innovative FL pruning framework that utilizes Discriminative Data (DD). Specifically, we utilize minimally pre-trained local models, allowing each client to extract semantic concepts as DD, which then inform an iterative pruning process. As a result, DDPruneFL significantly outperforms existing methods on four benchmark datasets, adeptly handling both IID and non-IID distributions and Client Selection scenarios. This model achieves state-of-the-art (SOTA) performance in this field. Moreover, our studies comprehensively validate the effectiveness of DD. Furthermore, a detailed computational complexity analysis focused on Floating-point Operations (FLOPs) is also conducted. The FLOPs analysis reveals that DDPruneFL significantly improves performance during inference while only marginally increasing training costs. Additionally, it exhibits a cost advantage in inference when compared to other pruning FL methods of the same type, further emphasizing its cost-effectiveness and practicality.

Federated cloud, as a promising technology, can improve the computing capacity for autonomous driving in the vehicle-road-cloud collaborative system. However, the allocation of federated clouds should consider the environmental changes based on the real-time impact of vehicle terminal location. To improve computational efficiency while ensuring the effectiveness of federated clouds, this paper proposes a one-sided matching reverse auction based on the federated clouds (OSFC) method for scheduling autonomous driving sensors in a vehicle-road-cloud collaborative environment. This method dynamically allocates communication resources according to the actual situation of the vehicle terminals in real time. Numerical simulations show that our proposed OSFC method significantly improves computational efficiency while ensuring the effectiveness of federated clouds compared with state-of-the-art work.

In this paper, we present a framework for composing discrete-event simulation models from a large amount of airspace traffic data without using any specific waypoints. The framework consists of two parts. In the first part, abstracted route graphs that indicate representative routes in the airspace are composed. We propose two methods for extracting important routes in the form of graphs based on combination of various technologies such as space partition, trajectory clustering, and skeleton extraction. In the second part, discrete-event simulation models are composed based on statistical information on flight time along each edge of the abstracted route graph. The composed simulation models have intermediate granularity between micro models, such as multi-agent simulation, and macro models, such as queuing models, and therefore they should be classified as mesoscopic models. Finally, we show numerical results to evaluate the accuracy of the simulation model.

Accurate water level prediction systems improve safety and quality of life. This study introduces a method that uses clustering and deep learning of multisite data to enhance the water level prediction of the Three Gorges Dam. The results show that Cluster-GRU-based can provide accurate forecasts for up to seven days.

In recent times, there has been a significant focus on the development of automotive high-resolution 77 GHz CS (Chirp Sequence) radar, a technology essential for autonomous driving. However, with the increasing popularity of vehicle-mounted CS radars, the issue of intensive inter-radar wideband interference has emerged as a significant concern, leading to undesirable missed targe detection. To solve this problem, various algorithm and learning based approaches have been proposed for wideband interference suppression. In this study, we begin by conducting extensive simulations to assess the SINR (Signal to Interference plus Noise Ratio) and execution time of these approaches in highly demanding scenarios involving up to 7 interfering radars. Subsequently, to validate these approaches could generalize to real data, we perform comprehensive experiments on inter-radar interference using multiple 77 GHz MIMO (Multiple-Input and Multiple-output) CS radars. The collected real-world interference data is then utilized to validate the generalization capacity of these approaches in terms of SINR, missed detection rate, and false detection rate.

With the development of the Semantic Web, an increasing number of researchers are utilizing ontology technology to construct domain ontology. Since there is no unified construction standard, ontology heterogeneity occurs. The ontology matching method can fuse heterogeneous ontologies, which realizes the interoperability between knowledge and associates to more relevant semantic information. In the case of differences between ontologies, how to reduce false matching and unsuccessful matching is a critical problem to be solved. Moreover, as the number of ontologies increases, the semantic relationship between ontologies becomes increasingly complex. Nevertheless, the current methods that solely find the similarity of names between concepts are no longer sufficient. Consequently, this paper proposes an ontology matching method based on semantic association. Accurate matching pairs are discovered by existing semantic knowledge, and then the potential semantic associations between concepts are mined according to the characteristics of the contextual structure. The matching method can better carry out matching work based on reliable knowledge. In addition, this paper introduces a probabilistic logic repair method, which can detect and repair the conflict of matching results, to enhance the availability and reliability of matching results. The experimental results show that the proposed method effectively improves the quality of matching between ontologies and saves time on repairing incorrect matching pairs. Besides, compared with the existing ontology matching systems, the proposed method has better stability.

In order to calculate photonic devices with slowly varying waveguide structure along propagation direction, we develop finite element beam propagation method (FE-BPM) with coordinate transformation. In this approach, converting a longitudinally varying waveguide into the equivalent straight waveguide, cumbersome processes in FE-BPM, such as mesh updating and field interpolation processes at each propagation step, can be avoided. We employ this simulation technique in shape optimization of photonic devices and show design examples of mode converter. To show the validity of this approach, the calculated results of designed devices are compared with the finite element method (FEM) or the standard FE-BPM.

The task of Speech Emotion Detection (SED) aims at judging positive class and negetive class when the speaker expresses emotions. The SED performances are heavily dependent on the diversity and prominence of emotional features extracted from the speech. However, most of the existing related research focuses on investigating the effects of single feature source and hand-crafted features. Thus, we propose a SED approach using multi-source low-level information based recurrent branches. The fusion multi-source low-level information obtain variety and discriminative representations from speech emotion signals. In addition, focal-loss function benifit for imbalance classes, resulting in reducing the proportion of well-classified samples and increasing the weights for difficult samples on SED tasks. Experiments on IEMOCAP corpus demonstrate the effectiveness of the proposed method. Compared with the baselines, MSIR achieve the significant performance improvements in terms of Unweighted Average Recall and F1-score.

This paper presents a comprehensive design approach to load-independent radio frequency (RF) power amplifiers. We project the zero-voltage-switching (ZVS) and zero-voltage-derivative-switching (ZVDS) load impedances onto a Smith chart, and find that their loci exhibit geodesic arcs. We exploit a two-port reactive network to convert the geodesic locus into another geodesic. This is named geodesic-to-geodesic (G2G) impedance conversion, and the power amplifier that employs G2G conversion is called class-G2G amplifier. We comprehensively explore the possible circuit topologies, and find that there are twenty G2G networks to create class-G2G amplifiers. We also find out that the class-G2G amplifier behaves like a transformer or a gyrator converting from dc to RF. The G2G design theory is verified via a circuit simulation. We also verified the theory through an experiment employing a prototype 100 W amplifier at 6.78 MHz. We conclude that the presented design approach is quite comprehensive and useful for the future development of high-efficiency RF power amplifiers.

Integrating RGB and event sensors improves object detection accuracy, especially during the night, due to the high-dynamic range of event camera. However, introducing an event sensor leads to an increase in computational resources, which makes the implementation of RGB-event fusion multi-modal AI to CiM difficult. To tackle this issue, this paper proposes RGB-Event fusion Multi-modal analog Computation-in-Memory (CiM), called REM-CiM, for multi-modal edge object detection AI. In REM-CiM, two proposals about multi-modal AI algorithms and circuit implementation are co-designed. First, Memory capacity-Efficient Attentional Feature Pyramid Network (MEA-FPN), the model architecture for RGB-event fusion analog CiM, is proposed for parameter-efficient RGB-event fusion. Convolution-less bi-directional calibration (C-BDC) in MEA-FPN extracts important features of each modality with attention modules, while reducing the number of weight parameters by removing large convolutional operations from conventional BDC. Proposed MEA-FPN w/ C-BDC achieves a 76% reduction of parameters while maintaining mean Average Precision (mAP) degradation to < 2.3% during both day and night, compared with Attentional FPN fusion (A-FPN), a conventional BDC-adopted FPN fusion. Second, the low-bit quantization with clipping (LQC) is proposed to reduce area/energy. Proposed REM-CiM with MEA-FPN and LQC achieves almost the same memory cells, 21% less ADC area, 24% less ADC energy and 0.17% higher mAP than conventional FPN fusion CiM without LQC.

Chinese-Vietnamese cross-lingual event retrieval aims to retrieve the Vietnamese sentence describing the same event as a given Chinese query sentence from a set of Vietnamese sentences. Existing mainstream cross-lingual event retrieval methods rely on extracting textual representations from query texts and calculating their similarity with textual representations in other language candidate sets. However, these methods ignore the difference in event elements present during Chinese-Vietnamese cross-language retrieval. Consequently, sentences with similar meanings but different event elements may be incorrectly considered to describe the same event. To address this problem, we propose a cross-lingual retrieval method that integrates event elements. We introduce event elements as an additional supervisory signal, where we calculate the semantic similarity of event elements in two sentences using an attention mechanism to determine the attention score of the event elements. This allows us to establish a one-to-one correspondence between event elements in the text. Additionally, we leverage the multilingual pre-trained language model fine-tuned based on contrastive learning to obtain cross-language sentence representation to calculate the semantic similarity of the sentence texts. By combining these two approaches, we obtain the final text similarity score. Experimental results demonstrate that our proposed method achieves higher retrieval accuracy than the baseline model.

The rapid advancement of cloud-edge-end collaboration offers a feasible solution to realize low-delay and low-energy-consumption data processing for internet of things (IoT)-based smart distribution grid. The major concern of cloud-edge-end collaboration lies on resource management. However, the joint optimization of heterogeneous resources involves multiple timescales, and the optimization decisions of different timescales are intertwined. In addition, burst electromagnetic interference will affect the channel environment of the distribution grid, leading to inaccuracies in optimization decisions, which can result in negative influences such as slow convergence and strong fluctuations. Hence, we propose a cloud-edge-end collaborative multi-timescale multi-service resource management algorithm. Large-timescale device scheduling is optimized by sliding window pricing matching, which enables accurate matching estimation and effective conflict elimination. Small-timescale compression level selection and power control are jointly optimized by disturbance-robust upper confidence bound (UCB), which perceives the presence of electromagnetic interference and adjusts exploration tendency for convergence improvement. Simulation outcomes illustrate the excellent performance of the proposed algorithm.

We propose a pre-T event-triggered controller (ETC) for the stabilization of a chain of integrators. Our per-T event-triggered controller is a modified event-triggered controller by adding a pre-defined positive constant T to the event-triggering condition. With this pre-T, the immediate advantages are (i) the often complicated additional analysis regarding the Zeno behavior is no longer needed, (ii) the positive lower bound of interexecution times can be specified, (iii) the number of control input updates can be further reduced. We carry out the rigorous system analysis and simulations to illustrate the advantages of our proposed method over the traditional event-triggered control method.