This paper presents a novel cooperative recording scheme in networked PVRs based on P2P networks to increase storage efficiency compared with when PVRs operate independently of each other, while maintaining program availability to a similar degree. We employ an erasure coding technique to guarantee data availability of recorded programs in P2P networks. We determine the data redundancy degree of recorded programs so that the system can support all the concurrent streaming requests for them and maintain as much availability as needed. We also present how to assign recording tasks to PVRs and playback the recorded programs without performance degradation. We show that our proposed scheme improves the storage efficiency significantly, compared with when PVRs do not cooperate with each other, while keeping the playbackability of each request similarly.

In this paper, we consider the transmission needs of communication networks for two classes of secondary users (SUs), named SU1 and SU2 (lowest priority) in cognitive radio networks (CRNs). In such CRNs, primary users (PUs) have preemptive priority over both SU1's users (SU1s) and SU2's users (SU2s). We propose a preemptive scheme (referred to as the P Scheme) and a non-preemptive scheme (referred to as the Non-P Scheme) when considering the interactions between SU1s and SU2s. Focusing on the transmission interruptions to SU2 packets, we present a probabilistic returning scheme with a returning probability to realize feedback control for SU2 packets. We present a Markov chain model to develop some formulas for SU1 and SU2 packets, and compare the influences of the P Scheme and the Non-P Scheme in the proposed probabilistic returning scheme. Numerical analyses compare the impact of the returning probability on the P Scheme and the Non-P Scheme. Furthermore, we optimize the returning probability and compare the optimal numerical results yielded by the P Scheme and the Non-P Scheme.

In spite of the research for a linear layer of Type-2 Generalized Feistel Network (Type-2 GFN) over more than 10 years, finding a good 32-branch permutation for Type-2 GFN is still a very hard task due to a huge search space. In terms of the diffusion property, Suzaki and Minematsu investigated the required number of rounds to achieve the full diffusion when the branch number is up to 16. After that, Derbez et al. presented a class of 32-branch permutations that achieves the 9-round full diffusion and they prove that this is optimal. However, this class is not suitable to be used in Type-2 GFN because it requires a large number of rounds to ensure a sufficient number of active S-boxes. In this paper, we present how to find a good class of 32-branch permutations for Type-2 GFN. To achieve this goal, we convert Type-2 GFN into a LBlock-like structure, and then we evaluate the diffusion property and the resistance against major attacks, such as differential, linear, impossible differential and integral attacks by an MILP. As a result, we present a good class of 32-branch permutations that achieves the 10-round full diffusion, ensures differentially/linearly active S-boxes of 66 at 19 round, and has the 18/20-round impossible differential/integral distinguisher, respectively. The 32-branch permutation used in WARP was chosen among this class.

A backdoor attack is a type of attack method inducing deep neural network (DNN) misclassification. An adversary mixes poison data, which consist of images tampered with adversarial marks at specific locations and of adversarial target classes, into a training dataset. The backdoor model classifies only images with adversarial marks into an adversarial target class and other images into the correct classes. However, the attack performance degrades sharply when the location of the adversarial marks is slightly shifted. An adversarial mark that induces the misclassification of a DNN is usually applied when a picture is taken, so the backdoor attack will have difficulty succeeding in the physical world because the adversarial mark position fluctuates. This paper proposes a new approach in which an adversarial mark is applied using fault injection on the mobile industry processor interface (MIPI) between an image sensor and the image recognition processor. Two independent attack drivers are electrically connected to the MIPI data lane in our attack system. While almost all image signals are transferred from the sensor to the processor without tampering by canceling the attack signal between the two drivers, the adversarial mark is injected into a given location of the image signal by activating the attack signal generated by the two attack drivers. In an experiment, the DNN was implemented on a Raspberry pi 4 to classify MNIST handwritten images transferred from the image sensor over the MIPI. The adversarial mark successfully appeared in a specific small part of the MNIST images using our attack system. The success rate of the backdoor attack using this adversarial mark was 91%, which is much higher than the 18% rate achieved using conventional input image tampering.

Deep learning applications have often been processed in the cloud or on servers. Still, for applications that require privacy protection and real-time processing, the execution environment is moved to edge devices. Edge devices that implement a neural network (NN) are physically accessible to an attacker. Therefore, physical attacks are a risk. Fault attacks on these devices are capable of misleading classification results and can lead to serious accidents. Therefore, we focus on the softmax function and evaluate a fault attack using a clock glitch against NN implemented in an 8-bit microcontroller. The clock glitch is used for fault injection, and the injection timing is controlled by monitoring the power waveform. The specific waveform is enrolled in advance, and the glitch timing pulse is generated by the sum of absolute difference (SAD) matching algorithm. Misclassification can be achieved by appropriately injecting glitches triggered by pattern detection. We propose a countermeasure against fault injection attacks that utilizes the randomization of power waveforms. The SAD matching is disabled by random number initialization on the summation register of the softmax function.

Low power consumption is important in edge artificial intelligence (AI) chips, where power supply is limited. Therefore, we propose reconfigurable neural network accelerator (ReNA), an AI chip that can process both a convolutional layer and fully connected layer with the same structure by reconfiguring the circuit. In addition, we developed tools for pre-evaluation of the performance when a deep neural network (DNN) model is implemented on ReNA. With this approach, we established the flow for the implementation of DNN models on ReNA and evaluated its power consumption. ReNA achieved 1.51TOPS/W in the convolutional layer and 1.38TOPS/W overall in a VGG16 model with a 70% pruning rate.

Along with the fast development of blue economy, wireless communication in oceans has received extensive attention in recent years, and opportunistic networks without any aid from fixed infrastructure or centralized management are expected to play an important role in such highly dynamic environments. Here, link prediction can help nodes to select proper links for data forwarding to reduce transmission failure. The existing prediction schemes are mainly based on analytical models with no adaptability, and consider relatively simple and small terrestrial wireless networks. In this paper, we propose a new link prediction algorithm based on machine learning, which is composed of an extractor of convolutional layers and an estimator of long short-term memory to extract useful representations of time-series data and identify effective long-term dependencies. The experiments manifest that the proposed scheme is more effective and flexible compared with the other link prediction schemes.

This paper presents a driver status monitoring (DSM) system with body channel communication (BCC) technology to acquire the driver's physiological condition. Specifically, a conductive thread, the receiving electrode, is sewn to the surface of the seat so that the acquired signal can be continuously detected. As a signal transmission medium, body channel characteristics using the conductive thread electrode were investigated according to the driver's pose and the material of the driver's pants. Based on this, a BCC transceiver was implemented using an analog frequency modulation (FM) scheme to minimize the additional circuitry and system cost. We analyzed the heart rate variability (HRV) from the driver's electrocardiogram (ECG) and displayed the heart rate and Root Mean Square of Successive Differences (RMSSD) values together with the ECG waveform in real-time. A prototype of the DSM system with commercial-off-the-shelf (COTS) technology was implemented and tested. We verified that the proposed approach was robust to the driver's movements, showing the feasibility and validity of the DSM with BCC technology using a conductive thread electrode.

This paper proposes a network tomography scheme for information-centric networking (ICN), which we call ICN tomography. When content is received over a conventional IP network, the communication occurs after converting the content name into an IP address, which is the locator, so as to identify the position of the network. By contrast, in ICN, communication is achieved by directly specifying the content name or content ID. The content is sent to the requesting user by a nearby node having the content or cache, making it difficult to apply a conventional network tomography that uses end-to-end quality of service (QoS) measurements and routing information between the source and destination node pairs as input to the ICN. This is because, in ICN, the end-to-end flow for an end host receiving some content can take various routes; therefore, the intermediate and source nodes can vary. In this paper, we first describe the technical challenges of applying network tomography to ICN. We then propose ICN tomography, where we use the content name as an endpoint to define an end-to-end QoS measurement and a routing matrix. In defining the routing matrix, we assume that the end-to-end flow follows a probabilistic routing. Finally, the effectiveness of the proposed method is evaluated through a numerical analysis and simulation.

Many cloud service providers employ specialized hardware accelerators, called neural processing units (NPUs), to accelerate deep neural networks (DNNs). An NPU scheduler is responsible for scheduling incoming user requests and required to satisfy the two, often conflicting, optimization goals: maximizing system throughput and satisfying quality-of-service (QoS) constraints (e.g., deadlines) of individual requests. We propose Layerweaver+, a low-cost layer-wise DNN scheduler for NPUs, which provides both high system throughput and minimal QoS violations. For a serving scenario based on the industry-standard MLPerf inference benchmark, Layerweaver+ significantly improves the system throughput by up to 266.7% over the baseline scheduler serving one DNN at a time.

We propose an attention mechanism in deep learning networks for gender recognition using the gaze distribution of human observers when they judge the gender of people in pedestrian images. Prevalent attention mechanisms spatially compute the correlation among values of all cells in an input feature map to calculate attention weights. If a large bias in the background of pedestrian images (e.g., test samples and training samples containing different backgrounds) is present, the attention weights learned using the prevalent attention mechanisms are affected by the bias, which in turn reduces the accuracy of gender recognition. To avoid this problem, we incorporate an attention mechanism called gaze-guided self-attention (GSA) that is inspired by human visual attention. Our method assigns spatially suitable attention weights to each input feature map using the gaze distribution of human observers. In particular, GSA yields promising results even when using training samples with the background bias. The results of experiments on publicly available datasets confirm that our GSA, using the gaze distribution, is more accurate in gender recognition than currently available attention-based methods in the case of background bias between training and test samples.

Front video and sensor data captured by vehicle-mounted event recorders are used for not only traffic accident evidence but also safe-driving education as near-miss traffic incident data. However, most event recorder (ER) data shows only regular driving events. To utilize near-miss data for safe-driving education, we need to be able to easily and rapidly locate the appropriate data from large amounts of ER data through labels attached to the scenes/events of interest. This paper proposes a method that can automatically identify near-misses with objects such as pedestrians and bicycles by processing the ER data. The proposed method extracts two deep feature representations that consider car status and the environment surrounding the car. The first feature representation is generated by considering the temporal transitions of car status. The second one can extract the positional relationship between the car and surrounding objects by processing object detection results. Experiments on actual ER data demonstrate that the proposed method can accurately identify and tag near-miss events.

Traffic congestion in road networks has been studied as the congestion game in game theory. In the existing work, the road usage by each agent was assumed to be static during the whole time horizon of the agent's travel, as in the classical congestion game. This assumption, however, should be reconsidered because each agent sequentially uses roads composing the route. In this paper, we propose a multi-agent distributed route selection scheme based on a gradient descent method considering the time-dependency among agents' road usage for vehicular networks. The proposed scheme first estimates the time-dependent flow on each road by considering the agents' probabilistic occupation under the first-in-first-out (FIFO) policy. Then, it calculates the optimal route choice probability of each route candidate using the gradient descent method and the estimated time-dependent flow. Each agent finally selects one route according to the optimal route choice probabilities. We first prove that the proposed scheme can exponentially converge to the steady-state at the convergence rate inversely proportional to the product of the number of agents and that of individual route candidates. Through simulations under a grid-like network and a real road network, we show that the proposed scheme can improve the actual travel time by 5.1% and 2.5% compared with the conventional static-flow based approach, respectively. In addition, we demonstrate that the proposed scheme is robust against incomplete information sharing among agents, which would be caused by its low penetration ratio or limited transmission range of wireless communications.

To safeguard critical services and assets in a distributed environment, collaborative intrusion detection systems (CIDSs) are usually adopted to share necessary data and information among various nodes, and enhance the detection capability. For simplifying the network management, software defined networking (SDN) is an emerging platform that decouples the controller plane from the data plane. Intuitively, SDN can help lighten the management complexity in CIDSs, and a CIDS can protect the security of SDN. In practical implementation, trust management is an important approach to help identify insider attacks (or malicious nodes) in CIDSs, but the challenge is how to ensure the data integrity when evaluating the reputation of a node. Motivated by the recent development of blockchain technology, in this work, we design BlockCSDN — a framework of blockchain-based collaborative intrusion detection in SDN, and take the challenge-based CIDS as a study. The experimental results under both external and internal attacks indicate that using blockchain technology can benefit the robustness and security of CIDSs and SDN.

The 2020 International Conference on Emerging Technologies for Communications (ICETC2020) was held online on December 2nd—4th, 2020, and 213 research papers were accepted and presented in each session. It is expected that the accepted papers will contribute to the development and extension of research in multiple research areas. In this survey paper, all accepted research papers are classified into four research areas: Physical & Fundamental, Communications, Network, and Information Technology & Application, and then research papers are classified into each research topic. For each research area and topic, this survey paper briefly introduces the presented technologies and methods.

The recommend system has been widely used in many web application areas such as e-commerce services. With the development of the recommend system, the HIN modeling method replaces the traditional bipartite graph modeling method to represent the recommend system. But several studies have already showed that recommend system is vulnerable to shilling attack (injecting attack). However, the effectiveness of how traditional shilling attack has rarely been studied directly in the HIN model. Moreover, no study has focused on how to enhance shilling attacks against HIN recommend system by using the high-level semantic information. This work analyzes the relationship between the high-level semantic information and the attacking effects in HIN recommend system. This work proves that attack results are proportional to the high-level semantic information. Therefore, we propose a heuristic attack method based on high-level semantic information, named Semantic Shilling Attack (SSA) on a HIN recommend system (HERec). This method injects a specific score into each selected item related to the target in semantics. It ensures transmitting the misleading information towards target items and normal users, and attempts to interfere with the effect of the recommend system. The experiment is dependent on two real-world datasets, and proves that the attacking effect is positively correlate with the number of meta-paths. The result shows that our method is more effective when compared with existing baseline algorithms.

Personalized news recommendation is becoming increasingly important for online news platforms to help users alleviate information overload and improve news reading experience. A key problem in news recommendation is learning accurate user representations to capture their interest. However, most existing news recommendation methods usually learn user representation only from their interacted historical news, while ignoring the clustering features among users. Here we proposed a hierarchical user preference hash network to enhance the representation of users' interest. In the hash part, a series of buckets are generated based on users' historical interactions. Users with similar preferences are assigned into the same buckets automatically. We also learn representations of users from their browsed news in history part. And then, a Route Attention is adopted to combine these two parts (history vector and hash vector) and get the more informative user preference vector. As for news representation, a modified transformer with category embedding is exploited to build news semantic representation. By comparing the hierarchical hash network with multiple news recommendation methods and conducting various experiments on the Microsoft News Dataset (MIND) validate the effectiveness of our approach on news recommendation.

Object contour detection is a task of extracting the shape created by the boundaries between objects in an image. Conventional methods limit the detection targets to specific categories, or miss-detect edges of patterns inside an object. We propose a new method to represent a contour image where the pixel value is the distance to the boundary. Contour detection becomes a regression problem that estimates this contour image. A deep convolutional network for contour estimation is combined with stereo vision to detect unspecified object contours. Furthermore, thanks to similar inference targets and common network structure, we propose a network that simultaneously estimates both contour and disparity with fully shared weights. As a result of experiments, the multi-tasking network drew a good precision-recall curve, and F-measure was about 0.833 for FlyingThings3D dataset. L1 loss of disparity estimation for the dataset was 2.571. This network reduces the amount of calculation and memory capacity by half, and accuracy drop compared to the dedicated networks is slight. Then we quantize both weights and activations of the network to 3-bit. We devise a dedicated hardware architecture for the quantized CNN and implement it on an FPGA. This circuit uses only internal memory to perform forward propagation calculations, that eliminates high-power external memory accesses. This circuit is a stall-free pixel-by-pixel pipeline, and performs 8 rows, 16 input channels, 16 output channels, 3 by 3 pixels convolution calculations in parallel. The convolution calculation performance at the operating frequency of 250 MHz is 9 TOPs/s.

TCP/IP, the foundation of the current Internet, assumes a sufficiently low packet loss rate for links in communication path. On the other hand, for communication services such as mobile and wireless communications, communication link tends to be disruptive. In this paper, we propose Layer-5 temporally-spliced path protocol (L5-TSPP), which provides disruption-tolerance in the L5 temporally-spliced path (L5-TSP), as one of the communication paths provided by Layer-5 (L5-paths). We design and implement an API for using L5-paths (L5 API). The L5 API is designed and implemented to support not only POSIX systems but also non-POSIX systems. L5 API and L5-TSPP are implemented in the user space in Go language. The measurement results show that L5-TSP achieves lower and more stable connection establishment time and better end-to-end throughput in the presence of disruption than conventional communication paths.

In this paper, we propose an image adjustment method for multi-exposure images based on convolutional neural networks (CNNs). We call image regions without information due to saturation and object moving in multi-exposure images lacking areas in this paper. Lacking areas cause the ghosting artifact in fused images from sets of multi-exposure images by conventional fusion methods, which tackle the artifact. To avoid this problem, the proposed method estimates the information of lacking areas via adaptive inpainting. The proposed CNN consists of three networks, warp and refinement, detection, and inpainting networks. The second and third networks detect lacking areas and estimate their pixel values, respectively. In the experiments, it is observed that a simple fusion method with the proposed method outperforms state-of-the-art fusion methods in the peak signal-to-noise ratio. Moreover, the proposed method is applied for various fusion methods as pre-processing, and results show obviously reducing artifacts.