Practical autoencoder based anomaly detection by using vector reconstruction error

Nowadays,cloud computing provides easy access to a set of variable and configurable computing resources based on user demand through the network.Cloud computing services are available through common internet protocols and network standards.n addition to the unique benefits of cloud computing,insecure communication and attacks on cloud networks cannot be ignored.There are several techniques for dealing with network attacks.To this end,network anomaly detection systems are widely used as an effective countermeasure against network anomalies.The anomaly-based approach generally learns normal traffic patterns in various ways and identifies patterns of anomalies.Network anomaly detection systems have gained much attention in intelligently monitoring network traffic using machine learning methods.This paper presents an efficient model based on autoencoders for anomaly detection in cloud computing networks.The autoencoder learns a basic representation of the normal data and its reconstruction with minimum error.Therefore,the reconstruction error is used as an anomaly or classification metric.In addition,to detecting anomaly data from normal data,the classification of anomaly types has also been investigated.We have proposed a new approach by examining an autoencoder's anomaly detection method based on data reconstruction error.Unlike the existing autoencoder-based anomaly detection techniques that consider the reconstruction error of all input features as a single value,we assume that the reconstruction error is a vector.This enables our model to use the reconstruction error of every input feature as an anomaly or classification metric.We further propose a multi-class classification structure to classify the anomalies.We use the CIDDS-001 dataset as a commonly accepted dataset in the literature.Our evaluations show that the performance of the proposed method has improved considerably compared to the existing ones in terms of accuracy,recall,false-positive rate,and F1-score metrics.

FREPD: A Robust Federated Learning Framework on Variational Autoencoder

Federated learning is an ideal solution to the limitation of not preser-ving the users’privacy information in edge computing.In federated learning,the cloud aggregates local model updates from the devices to generate a global model.To protect devices’privacy,the cloud is designed to have no visibility into how these updates are generated,making detecting and defending malicious model updates a challenging task.Unlike existing works that struggle to tolerate adversarial attacks,the paper manages to exclude malicious updates from the glo-bal model’s aggregation.This paper focuses on Byzantine attack and backdoor attack in the federated learning setting.We propose a federated learning frame-work,which we call Federated Reconstruction Error Probability Distribution(FREPD).FREPD uses a VAE model to compute updates’reconstruction errors.Updates with higher reconstruction errors than the average reconstruction error are deemed as malicious updates and removed.Meanwhile,we apply the Kolmogorov-Smirnov test to choose a proper probability distribution function and tune its parameters to fit the distribution of reconstruction errors from observed benign updates.We then use the distribution function to estimate the probability that an unseen reconstruction error belongs to the benign reconstruction error distribution.Based on the probability,we classify the model updates as benign or malicious.Only benign updates are used to aggregate the global model.FREPD is tested with extensive experiments on independent and identically distributed(IID)and non-IID federated benchmarks,showing a competitive performance over existing aggregation methods under Byzantine attack and backdoor attack.

STABLE AND ROBUST RECOVERY OF APPROXIMATELY k-SPARSE SIGNALS WITH PARTIAL SUPPORT INFORMATION IN NOISE SETTINGS VIA WEIGHTED ℓ_(p)(0

In the existing work,the recovery of strictly k-sparse signals with partial support information was derived in theℓ2 bounded noise setting.In this paper,the recovery of approximately k-sparse signals with partial support information in two noise settings is investigated via weightedℓp(0<p≤1)minimization method.The restricted isometry constant(RIC)conditionδt k<1 pη2 p−1+1 on the measurement matrix for some t∈[1+2−p 2+pσ,2]is proved to be sufficient to guarantee the stable and robust recovery of signals under sparsity defect in noisy cases.Herein,σ∈[0,1]is a parameter related to the prior support information of the original signal,andη≥0 is determined by p,t andσ.The new results not only improve the recent work in[17],but also include the optimal results by weightedℓ1 minimization or by standardℓp minimization as special cases.

Robust multifocus deep neural network for progression prediction on patient trajectory data

Purpose-Patient treatment trajectory data are used to predict the outcome of the treatment to particular disease that has been carried out in the research.In order to determine the evolving disease on the patient and changes in the health due to treatment has not considered existing methodologies.Hence deep learning models to trajectory data mining can be employed to identify disease prediction with high accuracy and less computation cost.Design/methodology/approach-Multifocus deep neural network classifiers has been utilized to detect the novel disease class and comorbidity class to the changes in the genome pattern of the patient trajectory data can be identified on the layers of the architecture.Classifier is employed to learn extracted feature set with activation and weight function and then merged on many aspects to classify the undetermined sequence of diseases as a new variant.The performance of disease progression learning progress utilizes the precision of the constituent classifiers,which usually has larger generalization benefits than those optimized classifiers.Findings-Deep learning architecture uses weight function,bias function on input layers and max pooling.Outcome of the input layer has applied to hidden layer to generate the multifocus characteristics of the disease,and multifocus characterized disease is processed in activation function using ReLu function along hyper parameter tuning which produces the effective outcome in the output layer of a fully connected network.Experimental results have proved using cross validation that proposed model outperforms methodologies in terms of computation time and accuracy.Originality/value-Proposed evolving classifier represented as a robust architecture on using objective function to map the data sequence into a class distribution of the evolving disease class to the patient trajectory.Then,the generative output layer of the proposed model produces the progression outcome of the disease of the particular patient trajectory.The model tries to produce the accurate prognosis outcomes by employing data conditional probability function.The originality of the work defines 70%and comparisons of the previous methods the method of values are accurate and increased analysis of the predictions.