Despite its success in many applications, federated learning is increasingly vulnerable to sophisticated poisoning attacks. Existing defenses, particularly Byzantine Robust Aggregation Rules (BRARs), offer some protection but rely on strong assumptions or challenging technical prerequisites. To address these shortcomings, we propose anensemble defense with provably convergent aggregation(EndPCA). By using the entropy weight method to consolidate scores from multiple BRARs into an ensemble trust score, it effectively integrates heterogeneous weak BRARs to resist a wide range of poisoning attacks under practical assumptions. We formally prove that EndPCA can provide theoretical guarantees of convergence with bounded error. Our empirical evaluations show that EndPCA consistently outperforms existing BRARs, demonstrating its effectiveness across various scenarios.

Precise mapping of crop types and estimating yields are important in gauging agricultural diversity and yield potential, especially in regions dominated by small-scale farming. Nevertheless, these tasks are challenging due to factors such as small field sizes, inter-cropping, and a lack of sufficient ground truth labels for certain regions. In this paper, we propose an approach that combines advanced deep learning algorithms with Sentinel-2 and MODIS satellite data for improving the accuracy of crop type mapping and yield prediction. We used datasets from the main growing season of 2017 in Kenya (Bungoma, Busia and Siaya) coupled with county level yield data from US, Argentina and Brazil spanning from 2005 to 2016. Our models (CNN, SegNet, MaskRCNN, ResNet, UNet) were evaluated on both tasks i.e., classification of crop types and predicting yields.

Insider threats pose significant security risks in distributed networks, because employees within the organisation may misuse their access to compromise systems. Centralised Machine Learning (ML) techniques are inappropriate in these situations due to privacy and data heterogeneity concerns. To address class imbalance and non-IID data, this study introduces FedAT, a Federated Adversarial Training that integrates federated learning (FL) with generative models to deliver privacy-preserving, multiclass Insider Threat Detection (ITD). FedAT outperforms centralized and conventional FL techniques in terms of scalability, privacy preservation, and detection accuracy, according to evaluations conducted on public CERT datasets.

One-Shot Federated Learning (OSFL) restricts communication between the server and clients to a single round, significantly reducing communication costs and minimizing privacy leakage risks compared to traditional Federated Learning (FL), which requires multiple rounds of communication. However, existing OSFL frameworks remain vulnerable to distributional heterogeneity, as they primarily focus on model heterogeneity while neglecting data heterogeneity. To bridge this gap, we propose FedHydra, a unified, data-free, OSFL framework designed to effectively address both model and data heterogeneity. Unlike existing OSFL approaches, FedHydra introduces a novel two-stage learning mechanism. Specifically, it incorporates model stratification and heterogeneity-aware stratified aggregation to mitigate the challenges posed by both model and data heterogeneity. By this design, the data and model heterogeneity issues are simultaneously monitored from different aspects during learning. Consequently, FedHydra can effectively mitigate both issues by minimizing their inherent conflicts. We compared FedHydra with five SOTA baselines on four benchmark datasets. Experimental results show that our method outperforms the previous OSFL methods in both homogeneous and heterogeneous settings. The code is available at https://github.com/Jun-B0518/FedHydra.

Federated Learning (FL) is a distributed machine learning technique where multiple devices (such as smartphones or IoT devices) train a shared global model by using their local data. FL claims that the data privacy of local participants is preserved well because local data will not be shared with either the server-side or other training participants. However, this paper discovers a pioneering finding that a model inversion (MI) attacker, who acts as a benign participant, can invert the shared global model and obtain the data belonging to other participants. This will lead to severe data-leakage risk in FL because it is difficult to identify attackers from benign participants. In addition, we found even the most advanced defense approaches could not effectively address this issue. Therefore, it is important to evaluate such data-leakage risks of an FL system before using it. To alleviate this issue, we propose FedInverse to evaluate whether the FL global model can be inverted by MI attackers. In particular, FedInverse can be optimized by leveraging the Hilbert-Schmidt independence criterion (HSIC) as a regularizer to adjust the diversity of the MI attack generator. We test FedInverse with three typical MI attackers, GMI, KED-MI, and VMI, and the experiments show our FedInverse method can successfully obtain the data belonging to other participants. The code of this work is available at https://github.com/Jun-B0518/FedInverse

Recently, the link prediction methods based on enclosing subgraph extraction and line graph transformation have been proven to achieve excellent prediction accuracy, but there are still some shortcomings, for examples, the time and space complexity of line graph transformation is too high and the graph neural network it used ignores the high-order relationship and local clustering structure between nodes, which makes it difficult to be widely used in real life and may affect the prediction accuracy. To solve the above problems, a hypergraph neural network model based on enclosing subgraph extraction is proposed, which converts subgraph into hypergraph by dual hypergraph transformation, and uses the hypergraph convolutional neural network to learn the higher-order features of nodes and edges respectively. After three experiments, the results show that the proposed model not only has higher prediction accuracy, but also has shorter runtime and less memory usage.

Federated Learning (FL) offers a novel distributed machine learning context whereby a global model is collaboratively learned through edge devices without violating data privacy. However, intrinsic data heterogeneity in the federated network can induce model heterogeneity, thus posing a great challenge to the server-side model aggregation performance. Existing FL algorithms widely adopt model-wise weighted averaging for client models to generate the new global model, which emphasizes the importance of the holistic model but ignores the importance of distinctions between internal parameters of various client models. In this paper, we propose a novel parameter-wise elastic weighted averaging aggregation approach to realize the rapid fusion of heterogeneous client models. Specifically, each client evaluates the importance of model internal parameters in the model update and obtains the corresponding parameter importance coefficient vector; the server implements the parameter-wise weighted averaging for each parameter based on their importance coefficient vectors, thereby aggregating a new global model. Extensive experiments on MNIST and CIFAR-10 datasets with diverse network architectures and hyper-parameter combinations show that our proposed algorithm outperforms the existing state-of-the-art FL algorithms on the performance of heterogeneous model fusion.

Insider threat analysis techniques based on machine learning provide convenient and effective automated detection of internally generated cyberattacks. When data are manipulated by adding slight perturbations, the threat intelligence models result in misclassifications of highly skewed class distribution with rare occurrences of events in insider threats. This paper proposes a generative model WGAN-GP conditioned by the class labels, referred to as CWGAN-GP, for insider threat analysis to create synthetic data samples for the rare malicious activities and shows that it generalizes well across different learning algorithms. Further, the robustness of the supervised algorithms to unknown inputs have not been investigated in any other works. This study explores how the synthetically created adversarial samples can increase the robustness of supervised models using adversarial training. We use a target classifier as threat model to generate one-step and iterative adversarial samples and perform a non-targeted test-time attack on the classifiers. We evaluate the robustness of various learning models against synthetic data from other data generation methods and demonstrate that the adversarial training using data generated from CWGAN-GP is less susceptible to adversarial attacks on insider threat classifiers using multiple versions of benchmark CMU CERT data set.

This study investigates the use of Augmented Reality (AR) generated analytics to measure the number of times a child can perform the action of crossing the midline by a drumming action. Using a prototype Drum AR App with gamification techniques to motivate the drumming actions with a drumstick, we can capture and log key metrics which measure the physical drumming actions such as the timings and the quality of crossing of the midline through game play. This study is still work in progress where further research on the uses and effectiveness of AR generated analytics can give insights to the development of perceptual motor skills in young children. Generating 2D and 3D plots from the AR generated analytics gives evidence to further identify novel metrics to capture, analyse and give insights to user interactions while using AR apps in learning.

Insider threats are the cyber attacks from the trusted entities within an organization. An insider attack is hard to detect as it may not leave a footprint and potentially cause huge damage to organizations. Anomaly detection is the most common approach for insider threat detection. Lack of real-world data and the skewed class distribution in the datasets makes insider threat analysis an understudied research area. In this paper, we propose a Conditional Generative Adversarial Network (CGAN) to enrich under-represented minority class samples to provide meaningful and diverse data for anomaly detection from the original malicious scenarios. Comprehensive experiments performed on benchmark dataset demonstrates the effectiveness of using CGAN augmented data, and the capability of multi-class anomaly detection for insider activity analysis. Moreover, the method is compared with other existing methods against different parameters and performance metrics.

SUMMARY: Circos plots are graphical outputs that display three dimensional chromosomal interactions and fusion transcripts. However, the Circos plot tool is not an interactive visualization tool, but rather a figure generator. For example, it does not enable data to be added dynamically nor does it provide information for specific data points interactively. Recently, an R-based Circos tool (RCircos) has been developed to integrate Circos to R, but similarly, Rcircos can only be used to generate plots. Thus, we have developed a Circos plot tool (J-Circos) that is an interactive visualization tool that can plot Circos figures, as well as being able to dynamically add data to the figure, and providing information for specific data points using mouse hover display and zoom in/out functions. J-Circos uses the Java computer language to enable, it to be used on most operating systems (Windows, MacOS, Linux). Users can input data into J-Circos using flat data formats, as well as from the Graphical user interface (GUI). J-Circos will enable biologists to better study more complex chromosomal interactions and fusion transcripts that are otherwise difficult to visualize from next-generation sequencing data. AVAILABILITY AND IMPLEMENTATION: J-circos and its manual are freely available at http://www.australianprostatecentre.org/research/software/jcircos CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: Small RNA sequencing is commonly used to identify novel miRNAs and to determine their expression levels in plants. There are several miRNA identification tools for animals such as miRDeep, miRDeep2 and miRDeep*. miRDeep-P was developed to identify plant miRNA using miRDeep's probabilistic model of miRNA biogenesis, but it depends on several third party tools and lacks a user-friendly interface. The objective of our miRPlant program is to predict novel plant miRNA, while providing a user-friendly interface with improved accuracy of prediction. RESULT: We have developed a user-friendly plant miRNA prediction tool called miRPlant. We show using 16 plant miRNA datasets from four different plant species that miRPlant has at least a 10% improvement in accuracy compared to miRDeep-P, which is the most popular plant miRNA prediction tool. Furthermore, miRPlant uses a Graphical User Interface for data input and output, and identified miRNA are shown with all RNAseq reads in a hairpin diagram. CONCLUSIONS: We have developed miRPlant which extends miRDeep* to various plant species by adopting suitable strategies to identify hairpin excision regions and hairpin structure filtering for plants. miRPlant does not require any third party tools such as mapping or RNA secondary structure prediction tools. miRPlant is also the first plant miRNA prediction tool that dynamically plots miRNA hairpin structure with small reads for identified novel miRNAs. This feature will enable biologists to visualize novel pre-miRNA structure and the location of small RNA reads relative to the hairpin. Moreover, miRPlant can be easily used by biologists with limited bioinformatics skills.miRPlant and its manual are freely available at http://www.australianprostatecentre.org/research/software/mirplant or http://sourceforge.net/projects/mirplant/.

In this paper, spherical harmonics are proposed as shape descriptors for 2d images. We introduce the concept of connectivity; 2d images are decomposed using connectivity which is followed by 3d model construction. Spherical harmonics are obtained for 3d models and used as descriptors for the underlying 2d shapes. Difference between two images is computed as the Euclidean distance between their spherical harmonics descriptors. Experiments are performed to test the effectiveness of spherical harmonics for retrieval of 2d images. Item S8 within the MPEG-7 Still Images Content Set is used for performing experiments; this dataset consists of 3621 still images. Experimental results show that the proposed descriptors for 2d images are effective.

Previously, we proposed the concept of connectivity to obtain discriminating shape descriptors. In this paper, we use connectivity to obtain superior distance histograms for multi-scale images. Experiments are performed to evaluate the distance histograms, based on connectivity, for shape-based retrieval of multi-scale images. Item S8 within the MPEG-7 still images content set is used for performing experiments. Experimental results show that the proposed method enhances retrieval performance significantly.

We propose a method for enhancing the accuracy of shape descriptors. The concept of connectivity to obtain discriminating shape descriptors, is introduced. We show how connectivity is applied to two popular shape descriptors. Experiments are performed to test the effect of using connectivity with generic Fourier descriptors and distance histograms. Item S8 within the MPEG-7 still images content set is used for performing experiments. This dataset consists of 3621 still images. The experimental results show that connectivity enhances the performance of the methods significantly.