Biblio

Existing anomaly detection models show success in detecting abnormal images with generative adversarial networks on the insufficient annotation of anomalous samples. However, existing models cannot accurately identify the anomaly samples which are close to the normal samples. We assume that the main reason is that these methods ignore the diversity of patterns in normal samples. To alleviate the above issue, this paper proposes a novel anomaly detection framework based on generative adversarial network, called ADe-GAN. More concretely, we construct a self-supervised learning task to fully explore the pattern information and latent representations of input images. In model inferring stage, we design a new abnormality score approach by jointly considering the pattern information and reconstruction errors to improve the performance of anomaly detection. Extensive experiments show that the ADe-GAN outperforms the state-of-the-art methods over several real-world datasets.

Advanced video compression is required due to the rise of online video content. A strong compression method can help convey video data effectively over a constrained bandwidth. We observed how more internet usage for video conferences, online gaming, and education led to decreased video quality from Netflix, YouTube, and other streaming services in Europe and other regions, particularly during the COVID-19 epidemic. They are represented in standard video compression algorithms as a succession of reference frames after residual frames, and these approaches are limited in their application. Deep learning's introduction and current advancements have the potential to overcome such problems. This study provides a deep learning-based video compression model that meets or exceeds current H.264 standards.

This paper addresses the issues in managing group key among clusters in Mobile Ad hoc Networks (MANETs). With the dynamic movement of the nodes, providing secure communication and managing secret keys in MANET is difficult to achieve. In this paper, we propose a distributed secure broadcast stateless groupkey management framework (DSBS-GKM) for efficient group key management. This scheme combines the benefits of hash function and Lagrange interpolation polynomial in managing MANET nodes. To provide a strong security mechanism, a revocation system that detects and revokes misbehaviour nodes is presented. The simulation results show that the proposed DSBS-GKM scheme attains betterments in terms of rekeying and revocation performance while comparing with other existing key management schemes.

Spear phishing emails target to specific individual or organization, they are more elaborated, targeted, and harmful than phishing emails. The attackers usually harvest information about the recipient in any available ways, then create a carefully camouflaged email and lure the recipient to perform dangerous actions. In this paper we present a new effective approach to detect spear phishing emails based on machine learning. Firstly we extracted 21 Stylometric features from email, 3 forwarding features from Email Forwarding Relationship Graph Database(EFRGD), and 3 reputation features from two third-party threat intelligence platforms, Virus Total(VT) and Phish Tank(PT). Then we made an improvement on Synthetic Minority Oversampling Technique(SMOTE) algorithm named KM-SMOTE to reduce the impact of unbalanced data. Finally we applied 4 machine learning algorithms to distinguish spear phishing emails from non-spear phishing emails. Our dataset consists of 417 spear phishing emails and 13916 non-spear phishing emails. We were able to achieve a maximum recall of 95.56%, precision of 98.85% and 97.16% of F1-score with the help of forwarding features, reputation features and KM-SMOTE algorithm.

It is not possible to speak about a complete security system without also taking into account the video surveillance system (CCTV). The reason is that CCTV systems offer the most spectacular results both in the security of goods and people and in the field of customer relations, marketing, traffic monitoring and the list can go on. With the development of the software industry the applicability of CCTV systems has greatly increased, largely due to image processing applications. The present paper, which is the continuation of an article already presented at an international conference, aims to shape the electrical characteristics of a common video surveillance system. The proposed method will be validated in two different programming environments.

In most correlation filter target tracking algorithms, poor accuracy in the tracking process for complex field images of the target and scale change problems. To address these issues, this paper proposes an algorithm of adaptive multi-feature fusion with scale change correlation filtering tracking. Our algorithm is based on the rapid and simple Kernel-Correlated Filtering(K CF) tracker, and achieves the complementarity among image features by fusing multiple features of Color Nmae(CN), Histogram of Oriented Gradient(HOG) and Local Binary Pattern(LBP) with weights adjusted by visual evaluation functions. The proposed algorithm introduces scale pooling and bilinear interpolation to adjust the target template size. Experiments on the OTB-2015 dataset of 100 video frames are compared with several trackers, and the precision and success ratio of our algorithm on complex scene tracking problems are 17.7% and 32.1 % respectively compared to the based-KCF.

Plenary Talk Our everyday life is more and more dependent on electronic communication and network connectivity. However, the threats of attacks and different types of misuse increase exponentially with the expansion of computer networks. In order to alleviate the problem and to identify malicious activities as early as possible Network Intrusion Detection Systems (NIDSs) have been developed and intensively investigated. Several approaches have been proposed and applied so far for these systems. It is a common challenge in this field that often there are no crisp boundaries between normal and abnormal network traffic, there are noisy or inaccurate data and therefore the investigated traffic could represent both attack and normal communication. Fuzzy logic based solutions could be advantageous owing to their capability to define membership levels in different classes and to do different operations with results ensuring reduced false positive and false negative classification compared to other approaches. In this presentation, after a short introduction of NIDSs a survey will be done on typical fuzzy logic based solutions followed by a detailed description of a fuzzy rule interpolation based IDS. The whole development process, i.e. data preprocessing, feature extraction, rule base generation steps are covered as well.

Bi-dimensional empirical mode decomposition can decompose the source image into several Bi-dimensional Intrinsic Mode Functions. In the process of image decomposition, interpolation is needed and the upper and lower envelopes will be drawn. However, these interpolations and the drawings of upper and lower envelopes require a lot of computation time and manual screening. This paper proposes a simple but effective method that can maintain the characteristics of the original BEMD method, and the Hermite interpolation reconstruction method is used to replace the surface interpolation, and the variable neighborhood window method is used to replace the fixed neighborhood window method. We call it fast bi-dimensional empirical mode decomposition of the variable neighborhood window method based on research characteristics, and we finally complete the image fusion. The empirical analysis shows that this method can overcome the shortcomings that the source image features and details information of BIMF component decomposed from the original BEMD method are not rich enough, and reduce the calculation time, and the fusion quality is better.

Surveillance cameras, which is a form of Cyber Physical System, are deployed extensively to provide visual surveillance monitoring of activities of interest or anomalies. However, these cameras are at risks of physical security attacks against their physical attributes or configuration like tampering of their recording coverage, camera positions or recording configurations like focus and zoom factors. Such adversarial alteration of physical configuration could also be invoked through cyber security attacks against the camera's software vulnerabilities to administratively change the camera's physical configuration settings. When such Cyber Physical attacks occur, they affect the integrity of the targeted cameras that would in turn render these cameras ineffective in fulfilling the intended security functions. There is a significant measure of research work in detection mechanisms of cyber-attacks against these Cyber Physical devices, however it is understudied area with such mechanisms against integrity attacks on physical configuration. This research proposes the use of the novel use of deep learning algorithms to detect such physical attacks originating from cyber or physical spaces. Additionally, we proposed the novel use of deep learning-based video frame interpolation for such detection that has comparatively better performance to other anomaly detectors in spatiotemporal environments.

Shamir's Secret Sharing Scheme is well established and widely used. It allows a so-called Dealer to split and share a secret k among n Participants such that at least t shares are needed to reconstruct k, where 0 \textbackslashtextbackslashtextless; t ≤ n. Nothing about the secret can be learned from less than t shares. To split secret k, the Dealer generates a polynomial f, whose independent term is k and the coefficients are randomly selected using a uniform distribution. A share is a pair (x, f(x)) where x is also chosen randomly using a uniform distribution. This scheme is useful, for example, to distribute cryptographic keys among different cloud providers and to create multi-factor authentication. The security of Shamir's Secret Sharing Scheme is usually analyzed using a threat model where the Dealer is trusted to split and share secrets as described above. In this paper, we demonstrate that there exists a different threat model where a malicious Dealer can compute shares such that a subset of less than t shares is allowed to reconstruct the secret. We refer to such subsets as hidden sets. We formally define hidden sets and prove lower bounds on the number of possible hidden sets for polynomials of degree t - 1. Yet, we show how to detect hidden sets given a set of n shares and describe how to create hidden sets while sharing a secret using a modification of Shamir's scheme.

Convolutional Neural Networks (CNN) have shown astonishing results in the field of computer vision. This paper proposes a foreground segmentation algorithm based on CNN to tackle the practical challenges in the video surveillance system such as illumination changes, dynamic backgrounds, camouflage, and static foreground object, etc. The network is trained using the input of image sequences with respective ground-truth. The algorithm employs a CNN called VGG-16 to extract features from the input. The extracted feature maps are upsampled using a bilinear interpolation. The upsampled feature mask is passed through a sigmoid function and threshold to get the foreground mask. Binary cross entropy is used as the error function to compare the constructed foreground mask with the ground truth. The proposed algorithm was tested on two standard datasets and showed superior performance as compared to the top-ranked foreground segmentation methods.

In this work, robust readout of the data (232 English characters) stored in high-security structural colour QR codes, was achieved by using multiple image processing techniques, specifically, histogram equalization and decorrelation stretching. The decoded structural colour QR codes are generic diffractive RGB-pixelated periodic nanocones selectively activated by laser exposure to obtain the particular design of interest. The samples were imaged according to the criteria determined by the diffraction grating equation for the lighting and viewing angles given the red, green, and blue periodicities of the grating. However, illumination variations all through the samples, cross-module and cross-channel interference effects result in acquiring images with dissimilar lighting conditions which cannot be directly retrieved by the decoding script and need significant preprocessing. According to the intensity plots, even if the intensity values are very close (above 200) at some typical regions of the images with different lighting conditions, their inconsistencies (below 100) at the pixels of one representative region may lead to the requirement for using different methods for recovering the data from all red, green, and blue channels. In many cases, a successful data readout could be achieved by downscaling the images to 300-pixel dimensions (along with bilinear interpolation resampling), histogram equalization (HE), linear spatial low-pass mean filtering, and gamma function, each used either independently or with other complementary processes. The majority of images, however, could be fully decoded using decorrelation stretching (DS) either as a standalone or combinational process for obtaining a more distinctive colour definition.

Dynamic Fuzzy Rule Interpolation (D-FRI) offers a dynamic rule base for fuzzy systems which is especially useful for systems with changing requirements and limited prior knowledge. This suggests a possible application of D-FRI in the area of network security due to the volatility of the traffic. A honeypot is a valuable tool in the field of network security for baiting attackers and collecting their information. However, typically designed with fewer resources they are not considered as a primary security tool for use in network security. Consequently, such honeypots can be vulnerable to many security attacks. One such attack is a spoofing attack which can cause severe damage to the honeypot, making it inefficient. This paper presents a vigilant dynamic honeypot based on the D-FRI approach for use in predicting and alerting of spoofing attacks on the honeypot. First, it proposes a technique for spoofing attack identification based on the analysis of simulated attack data. Then, the paper employs the identification technique to develop a D-FRI based vigilant dynamic honeypot, allowing the honeypot to predict and alert that a spoofing attack is taking place in the absence of matching rules. The resulting system is capable of learning and maintaining a dynamic rule base for more accurate identification of potential spoofing attacks with respect to the changing traffic conditions of the network.

Gatys et al. recently introduced a neural algorithm that renders a content image in the style of another image, achieving so-called style transfer. However, their framework requires a slow iterative optimization process, which limits its practical application. Fast approximations with feed-forward neural networks have been proposed to speed up neural style transfer. Unfortunately, the speed improvement comes at a cost: the network is usually tied to a fixed set of styles and cannot adapt to arbitrary new styles. In this paper, we present a simple yet effective approach that for the first time enables arbitrary style transfer in real-time. At the heart of our method is a novel adaptive instance normalization (AdaIN) layer that aligns the mean and variance of the content features with those of the style features. Our method achieves speed comparable to the fastest existing approach, without the restriction to a pre-defined set of styles. In addition, our approach allows flexible user controls such as content-style trade-off, style interpolation, color & spatial controls, all using a single feed-forward neural network.