The modern digitized world is mainly dependent on online services. The availability of online systems continues to be seriously challenged by distributed denial of service (DDoS) attacks. The challenge in mitigating attacks is not limited to identifying DDoS attacks when they happen, but also identifying the streams of attacks. However, existing attack detection methods cannot accurately and efficiently detect DDoS attacks. To this end, we propose an explainable artificial intelligence (XAI)-based novel method to identify DDoS attacks. This method detects abnormal behaviours of network traffic flows by analysing the traffic at the network layer. Moreover, it chooses the most influential features for each anomalous instance with influence weight and then sets a threshold value for each feature. Hence, this DDoS attack detection method defines security policies based on each feature threshold value for application-layer-based, volumetric-based, and transport control protocol (TCP) state-exhaustion-based features. Since the proposed method is based on layer three traffic, it can identify DDoS attacks on both Internet of Things (IoT) and traditional networks. Extensive experiments were performed on the University of Sannio, Benevento Instrution Detection System (USB-IDS) dataset, which consists of different types of DDoS attacks to test the performance of the proposed solution. The results of the comparison show that the proposed method provides greater detection accuracy and attack certainty than the state-of-the-art methods.

In the field of building detection research, an accurate, state-of-the-art semantic segmentation model must be constructed to classify each pixel of the image, which has an important reference value for the statistical work of a building area. Recent research efforts have been devoted to semantic segmentation using deep learning approaches, which can be further divided into two aspects. In this paper, we propose a single-side dual-branch network (SSDBN) based on an encoder–decoder structure, where an improved Res2Net model is used at the encoder stage to extract the basic feature information of prepared images while a dual-branch module is deployed at the decoder stage. An intermediate framework was designed using a new feature information fusion methods to capture more semantic information in a small area. The dual-branch decoding module contains a deconvolution branch and a feature enhancement branch, which are responsible for capturing multi-scale information and enhancing high-level semantic details, respectively. All experiments were conducted using the Massachusetts Buildings Dataset and WHU Satellite Dataset I (global cities). The proposed model showed better performance than other recent approaches, achieving an F1-score of 87.69% and an IoU of 75.83% with a low network size volume (5.11 M), internal parameters (19.8 MB), and GFLOPs (22.54), on the Massachusetts Buildings Dataset.

Over the past few decades, Machine Learning (ML)-based intrusion detection systems (IDS) have become increasingly popular and continue to show remarkable performance in detecting attacks. However, the lack of transparency in their decision-making process and the scarcity of attack data for training purposes pose a major challenge for the development of ML-based IDS systems for Internet of Things (IoT). Therefore, employing anomaly detection methods and interpreting predicted results in terms of feature contribution or performing featurebased impact analysis can increase stakeholders confidence. To this end, this paper presents a novel framework for IoT security monitoring, combining deep autoencoder models with Explainable Artificial Intelligence (XAI), to verify the credibility and certainty of attack detection by MLbased IDSs. Our proposed approach reduces the number of black boxes in the ML decision-making process in IoT security monitoring by explaining why a prediction is made, providing quantifiable data on which features influence the prediction and to what extent, which are generated from SHaply Adaptive values exPlanations (SHAP) linking optimal credit allocation to local explanations. This was tested using the USB-IDS benchmark dataset and a detection accuracy of 84% (benign) and 100% (attack) was achieved. Our experimental results show that integrating XAI with the autoencoder model obviates the need of malicious data for training purposes, but can provide attack certainty for detected anomalies, proving the validity of the proposed methodology.

In recent years, AI and Deep Learning (DL) methods have been widely used for object classification, recognition, and segmentation of high-resolution multispectral remote sensing images. These DL-based solutions perform better compare to traditional spectral algorithms but still suffer from insufficient optimization of global and local features of object context. In addition, failure of code-data isolation and/or disclosure of detailed eigenvalues causes serious privacy and even secret leakage due to the sensitivity of high-resolution remote sensing data and their processing mechanisms. In this paper, Class Feature (CF) modules have been presented in the decoder part of an attention-based CNN network to distinguish between building and non-building (background) area. In this way, context features of a focused object can be extracted with more details being processed, whilst the resolution of images is maintained. The reconstructed local and global feature values and dependencies in the proposed model are maintained by reconfiguring multiple effective attention modules with contextual dependencies to achieve better results for the eigenvalue. According to quantitative results and their visualization, the proposed model has depicted better performance over others' work using two largescale building remote sensing datasets. The F1-score of this model reached 87.91 and 89.58 on WHU Buildings Dataset and Massachusetts Buildings Dataset, respectively, which exceeded the other semantic segmentation models.

With the development of cloud computing and data intelligence, datacenters have become an important part of ensuring service quality and production efficiency in intelligent applications. However, datacenters are also facing increasingly complex and heavy task processing requirements currently, and more efficient scheduling methods are urgently needed. Therefore, this paper proposes a multi-swarm particle swarm optimization task scheduling method based on load balancing, aiming at reducing the maximum completion time (makespan) and response time in task scheduling. The proposed method designs a new fitness function for particles, and promotes the load balance of the cluster during the scheduling process by optimizing the combination of makespan and machine completion time variance. And a novel inertia weight is designed to dynamically adjust the particle search performance. The new initialization method and multi-swarm search design are used to improve the quality and diversity of solutions and avoid particles falling into local optimum. Finally, the proposed algorithm is verified experimentally using the task dataset released by Alibaba datacenter, and compared with other benchmark algorithms. The results show that the algorithm can improve the task scheduling performance of datacenters in supply chain management when dealing with different workloads and changes in the number of machines.