Networks had an increasing impact on modern life since network cybersecurity has become an important research field. Several machine learning techniques have been developed to build network intrusion ...detection systems for correctly detecting unforeseen cyber-attacks at the network-level. For example, deep artificial neural network architectures have recently achieved state-of-the-art results. In this paper a novel deep neural network architecture is defined, in order to learn flexible and effective intrusion detection models, by combining an unsupervised stage for multi-channel feature learning with a supervised one exploiting feature dependencies on cross channels. The aim is to investigate whether class-specific features of the network flows could be learned and added to the original ones in order to increase the model accuracy. In particular, in the unsupervised stage, two autoencoders are separately learned on normal and attack flows, respectively. As the top layer in the decoder of these autoencoders reconstructs samples in the same space as the input one, they could be used to define two new feature vectors allowing the representation of each network flow as a multi-channel sample. In the supervised stage, a multi-channel parametric convolution is adopted, in order to learn the effect of each channel on the others. In particular, as the samples belong to two different distributions (normal and attack flows), the samples labelled as normal should be more similar to the representation reconstructed with the normal autoencoder than that of the attack one, and viceversa. This expected dependency will be exploited to better disentangle the differences between normal and attack flows. The proposed neural network architecture leads to better predictive accuracy when compared to competitive intrusion detection architectures on three benchmark datasets.
Recognizing malware before its installation plays a crucial role in keeping an android device safe. In this paper we describe a supervised method that is able to analyse multiple information (e.g. ...permissions, api calls and network addresses) that can be retrieved through a broad static analysis of android applications. In particular, we propose a novel multi-view machine learning approach to malware detection, which couples knowledge extracted via both clustering and classification. In an assessment, we evaluate the effectiveness of the proposed method using benchmark Android applications and established machine learning metrics.
Recent long spells of high temperatures and drought-hit summers have fostered the conditions for an unprecedented outbreak of bark beetles in Europe. This phenomenon has ruined vast swathes of ...European conifer forests creating a need among forest managers to find effective methods to gather information about the mapping of bark beetle infestation hotspots. Sentinel-2 data have been recently established as an alternative to field surveys for certain inventory tasks. Hence, this study explores the achievements of machine learning to perform the inventory mapping of bark beetle infestation hotspots in Sentinel-2 images. In particular, we investigate the accuracy performance of a spectral classifier that is learned for the study task by leveraging spectral vegetation indices and performing self-training. We use a dataset of Sentinel-2 images acquired in nonoverlapping forest scenes from the North-east of France acquired in October 2018. The selected scenes host bark beetle infestation hotspots of different sizes, which originate from the mass reproduction of the bark beetle in the 2018 infestation. We perform a learning stage by accounting for the ground-truth bark beetle infestation masks of a subset of images in the study imagery dataset (training imagery set). The goal is to produce a prediction of the bark beetle infestation masks for the remaining images in the study imagery dataset (working imagery set). Moreover, we use an explainable artificial intelligence technique to study the relevance of spectral information and explain the effect of both self-training and spectral vegetation indices on the mapping decisions.
Various applications in remote sensing demand automatic detection of changes in optical satellite images of the same scene acquired over time. This paper investigates how to leverage autoencoders in ...change vector analysis, in order to better delineate possible changes in a couple of co-registered, optical satellite images. Let us consider both a primary image and a secondary image acquired over time in the same scene. First an autoencoder artificial neural network is trained on the primary image. Then the reconstruction of both images is restored via the trained autoencoder so that the spectral angle distance can be computed pixelwise on the reconstructed data vectors. Finally, a threshold algorithm is used to automatically separate the foreground changed pixels from the unchanged background. The assessment of the proposed method is performed in three couples of benchmark hyperspectral images using different criteria, such as overall accuracy, missed alarms and false alarms. In addition, the method supplies promising results in the analysis of a couple of multispectral images of the burned area in the Majella National Park (Italy).
•A DML methodology for network intrusion detection.•Triplet networks to deal with data imbalance.•Autoencoders to address the convergence problem of Triplet Networks.•A novel autoencoder-based ...predictive stage.•Experiments with benchmark datasets and various competitors.
Nowadays intrusion detection systems are a mandatory weapon in the war against the ever-increasing amount of network cyber attacks. In this study we illustrate a new intrusion detection method that analyses the flow-based characteristics of the network traffic data. It learns an intrusion detection model by leveraging a deep metric learning methodology that originally combines autoencoders and Triplet networks. In the training stage, two separate autoencoders are trained on historical normal network flows and attacks, respectively. Then a Triplet network is trained to learn the embedding of the feature vector representation of network flows. This embedding moves each flow close to its reconstruction, restored with the autoencoder associated with the same class as the flow, and away from its reconstruction, restored with the autoencoder of the opposite class. The predictive stage assigns each new flow to the class associated with the autoencoder that restores the closest reconstruction of the flow in the embedding space. In this way, the predictive stage takes advantage of the embedding learned in the training stage, achieving a good prediction performance in the detection of new signs of malicious activities in the network traffic. In fact, the proposed methodology leads to better predictive accuracy when compared to competitive intrusion detection architectures on benchmark datasets.
The recent boom in deep learning has revealed that the application of deep neural networks is a valuable way to address network intrusion detection problems. This paper presents a novel deep learning ...methodology that uses convolutional neural networks (CNNs) to equip a computer network with an effective means to analyse traffic on the network for signs of malicious activity. The basic idea is to represent network flows as 2D images and use this imagery representation of the flows to train a 2D CNN architecture. The novelty consists in deriving an imagery representation of the network flows through performing a combination of the nearest neighbour search and the clustering process. The advantage is that the proposed data mapping method allows us to build imagery data that express potential data patterns arising at neighbouring flows. The proposed methodology leads to better predictive accuracy when compared to competitive intrusion detection architectures on three benchmark datasets.
Nowadays attacks on computer networks continue to advance at a rate outpacing cyber defenders’ ability to write new attack signatures. This paper illustrates a deep learning methodology for the ...binary classification of the network traffic. The basic idea is to represent network flows as 2D images and use this imagery representation of the network traffic to train a Generative Adversarial Network (GAN) and a Convolutional Neural Network (CNN). The GAN is trained to produce new images of unforeseen network attacks by augmenting the training data used to learn a CNN-based intrusion detection model. The advantage is that the 2D data mapping technique used builds images of the network flows, which allow us to take advantage of deep learning architectures with convolution layers. In addition, the GAN-based data augmentation allows us to deal with the possible imbalance of malicious traffic that is commonly rarer than the normal traffic in the network traffic. Specifically, it is used to simulate unforeseen attacks to train a robust intrusion detection model. The proposed methodology leads to better predictive accuracy when compared to competitive intrusion detection architectures on four benchmark datasets.
•Image representation of network traffic data.•2D Convolutional Neural Networks for intrusion detection.•Generative Adversarial Networks to deal with data imbalance.•Experiments with benchmark datasets collected in different years.•Effectiveness of the method compared with recent, state-of-the-art competitors.
Change Detection (CD) aims to distinguish surface changes based on bi-temporal remote sensing images. In recent years, deep neural models have made a breakthrough in CD processes. However, training a ...deep neural model requires a large volume of labelled training samples that are time-consuming and labour-intensive to acquire. With the aim of learning an accurate CD model with limited labelled data, we propose SENECA: a method based on a CD Siamese network, which takes advantage of both Transfer Learning (TL) and Active Learning (AL) to handle the constraint of limited supervision. More precisely, we jointly use AL and TL to adapt a CD model trained on a labelled source domain to a (related) target domain featured by restricted access to labelled data. We report results from an experimental evaluation involving five pairs of images acquired via Sentinel-2 satellites between 2015 and 2018 in various locations picked all over Asia and USA. The results show the beneficial effects of the proposed AL and TL strategies on the accuracy of the decisions made by the CD Siamese network and depict the merit of the proposed approach over competing CD baselines.
•A Siamese network to detect changes in bi-temporal optical remote sensing images.•Transfer learning to adapt a model trained in a source domain to a target domain.•Segmentation-based active learning for transfer learning with weak supervision.•Experiments with Sentinel-2 imagery show the effectiveness of the method.
Vision Transformers (ViTs) denote a family of attention-based deep learning techniques that have recently achieved amazing results in various problems related to the field of computer vision. In this ...paper, we explore the use of ViTs in problems of cyber-threat detection related to malware and network intrusion detection. In particular, we propose VINCENT, that is a novel deep neural method, which resorts to a color imagery representation of cyber-data by encoding related cyber-data features into neighboring color pixels. ViTs are trained from cyber-data images as teacher models, to extract explainable imagery signatures of cyber-data classes. This knowledge is extracted by leveraging the self-attention mechanism to give paired attention values between pairs of imagery patches. The signature knowledge, extracted through the ViT teacher, is, finally, used to train a smaller neural student model according to the knowledge distillation theory. Experiments with various benchmark cybersecurity datasets assess the accuracy of the student model VINCENT also compared to that of several state-of-the-art methods. In addition, it shows that VINCENT can obtain insights from explanations recovered through the self-attention mechanism of the ViT teacher.
•ViTs trained on cyber-data images.•Explanation information distilled from ViTs to CNNs.•Experiments with four benchmark cybersecurity datasets.•The proposed method outperforms many state-of-the-art competitors.