Biblio

Currently, different forms of ransomware are increasingly threatening Internet users. Modern ransomware encrypts important user data, and it is only possible to recover it once a ransom has been paid. In this article we show how software-defined networking can be utilized to improve ransomware mitigation. In more detail, we analyze the behavior of popular ransomware - CryptoWall - and, based on this knowledge, propose two real-time mitigation methods. Then we describe the design of an SDN-based system, implemented using OpenFlow, that facilitates a timely reaction to this threat, and is a crucial factor in the case of crypto ransomware. What is important is that such a design does not significantly affect overall network performance. Experimental results confirm that the proposed approach is feasible and efficient.

In the field of image processing, it is more complex and challenging task to detect the Human motion in the video and recognize their actions from the video sequences. A novel approach is presented in this paper to detect the human motion and recognize their actions. By tracking the selected object over consecutive frames of a video or image sequences, the different Human actions are recognized. Initially, the background motion is subtracted from the input video stream and its binary images are constructed. Using spatiotemporal interest points, the object which needs to be monitored is selected by enclosing the required pixels within the bounding rectangle. The selected foreground pixels within the bounding rectangle are then tracked using edge tracking algorithm. The features are extracted and using these features human motion are detected. Finally, the different human actions are recognized using K-Nearest Neighbor classifier. The applications which uses this methodology where monitoring the human actions is required such as shop surveillance, city surveillance, airports surveillance and other important places where security is the prime factor. The results obtained are quite significant and are analyzed on the datasets like KTH and Weizmann dataset, which contains actions like bending, running, walking, skipping, and hand-waving.

Even though some seem to think privacy is dead, we are all still wearing clothes, as Bruce Schneier observed at a recent conference on surveillance[1]. Yet big data and big data analytics are leaving some of us feeling a bit more naked than before. This talk will provide some personal observations on privacy today and then outline some research areas where progress is needed to enable society to gain the benefits of analyzing large datasets without giving up more privacy than necessary. Not since the early 1970s, when computing pioneer Willis Ware chaired the committee that produced the initial Fair Information Practice Principles [2] has privacy been so much in the U.S. public eye. Snowden's revelations, as well as a growing awareness that merely living our lives seems to generate an expanding "digital exhaust." Have triggered many workshops and meetings. A national strategy for privacy research is in preparation by a Federal interagency group. The ability to analyze large datasets rapidly and to extract commercially useful insights from them is spawning new industries. Must this industrial growth come at the cost of substantial privacy intrusions?

Nowadays, many computer vision techniques are applied to practical applications, such as surveillance and facial recognition systems. Some of such applications focus on information extraction from the human beings. However, people may feel psychological stress about recording their personal information, such as a face, behavior, and cloth. Therefore, privacy protection of the images and videos is necessary. Specifically, the detection and tracking methods should be used on the privacy protected images. For this purpose, there are some easy methods, such as blurring and pixelating, and they are often used in news programs etc. Because such methods just average pixel values, no important feature for the detection and tracking is left. Hence, the preprocessed images are unuseful. In order to solve this problem, we have proposed shuffle filter and a multi-view face tracking method with a genetic algorithm (GA). The filter protects the privacy by changing pixel locations, and the color information can be preserved. Since the color information is left, the tracking can be achieved by a basic template matching with histogram. Moreover, by using GA instead of sliding window when the subject in the image is searched, it can search more efficiently. However, the tracking accuracy is still low and the preprocessing time is large. Therefore, improving them is the purpose in this research. In the experiment, the improved method is compared with our previous work, CAMSHIFT, an online learning method, and a face detector. The results indicate that the accuracy of the proposed method is higher than the others.

Automated human facial image de-identification is a much needed technology for privacy-preserving social media and intelligent surveillance applications. Other than the usual face blurring techniques, in this work, we propose to achieve facial anonymity by slightly modifying existing facial images into "averaged faces" so that the corresponding identities are difficult to uncover. This approach preserves the aesthesis of the facial images while achieving the goal of privacy protection. In particular, we explore a deep learning-based facial identity-preserving (FIP) features. Unlike conventional face descriptors, the FIP features can significantly reduce intra-identity variances, while maintaining inter-identity distinctions. By suppressing and tinkering FIP features, we achieve the goal of k-anonymity facial image de-identification while preserving desired utilities. Using a face database, we successfully demonstrate that the resulting "averaged faces" will still preserve the aesthesis of the original images while defying facial image identity recognition.

Applications such as fleet management and logistics, emergency response, public security and surveillance or mobile workforce management use geo-positioning and mobile networks as means of enabling real-time monitoring, communication and collaboration among a possibly large set of mobile nodes. The majority of those systems require real-time tracking of mobile nodes (e.g. vehicles, people or mobile robots), reliable communication to/from the nodes, as well as group communication among the mobile nodes. In this paper we describe a distributed middleware with focus on management of context-defined groups of mobile nodes, and group communication with large sets of nodes. We also present a prototype Fleet Tracking and Management system based on our middleware, give an example of how context-specific group communication can enhance the node's mutual awareness, and show initial performance results that indicate small overhead and latency of the group communication and management.

In this paper, an algorithm is proposed to automatically produce hierarchical graph-based representations of maritime shipping lanes extrapolated from historical vessel positioning data. Each shipping lane is generated based on the detection of the vessel behavioural changes and represented in a compact synthetic route composed of the network nodes and route segments. The outcome of the knowledge discovery process is a geographical maritime network that can be used in Maritime Situational Awareness (MSA) applications such as track reconstruction from missing information, situation/destination prediction, and detection of anomalous behaviour. Experimental results are presented, testing the algorithm in a specific scenario of interest, the Dover Strait.
 

The research question of this study is: How Integration Readiness Level (IRL) metrics can be understood and realized in the domain of border control information systems. The study address to the IRL metrics and their definition, criteria, references, and questionnaires for validation of border control information systems in case of the shared maritime situational awareness system. The target of study is in improvements of ways for acceptance, operational validation, risk assessment, and development of sharing mechanisms and integration of information systems and border control information interactions and collaboration concepts in Finnish national and European border control domains.
 

The need for increased surveillance due to increase in flight volume in remote or oceanic regions outside the range of traditional radar coverage has been fulfilled by the advent of space-based Automatic Dependent Surveillance — Broadcast (ADS-B) Surveillance systems. ADS-B systems have the capability of providing air traffic controllers with highly accurate real-time flight data. ADS-B is dependent on digital communications between aircraft and ground stations of the air route traffic control center (ARTCC); however these communications are not secured. Anyone with the appropriate capabilities and equipment can interrogate the signal and transmit their own false data; this is known as spoofing. The possibility of this type of attacks decreases the situational awareness of United States airspace. The purpose of this project is to design a secure transmission framework that prevents ADS-B signals from being spoofed. Three alternative methods of securing ADS-B signals are evaluated: hashing, symmetric encryption, and asymmetric encryption. Security strength of the design alternatives is determined from research. Feasibility criteria are determined by comparative analysis of alternatives. Economic implications and possible collision risk is determined from simulations that model the United State airspace over the Gulf of Mexico and part of the airspace under attack respectively. The ultimate goal of the project is to show that if ADS-B signals can be secured, the situational awareness can improve and the ARTCC can use information from this surveillance system to decrease the separation between aircraft and ultimately maximize the use of the United States airspace.

Communicating vehicles will change road traffic as we know it. With current versions of European and US standards in mind, the authors discuss privacy and traffic surveillance issues in vehicular network technology and outline research directions that could address these issues.

We propose a method for analysis of surveillance video by using low rank and sparse decomposition (LRSD) with low latency combined with compressive sensing to segment the background and extract moving objects in a surveillance video. Video is acquired by compressive measurements, and the measurements are used to analyze the video by a low rank and sparse decomposition of a matrix. The low rank component represents the background, and the sparse component, which is obtained in a tight wavelet frame domain, is used to identify moving objects in the surveillance video. An important feature of the proposed low latency method is that the decomposition can be performed with a small number of video frames, which reduces latency in the reconstruction and makes it possible for real time processing of surveillance video. The low latency method is both justified theoretically and validated experimentally.

To reduce human efforts in browsing long surveillance videos, synopsis videos are proposed. Traditional synopsis video generation applying optimization on video tubes is very time consuming and infeasible for real-time online generation. This dilemma significantly reduces the feasibility of synopsis video generation in practical situations. To solve this problem, the synopsis video generation problem is formulated as a maximum a posteriori probability (MAP) estimation problem in this paper, where the positions and appearing frames of video objects are chronologically rearranged in real time without the need to know their complete trajectories. Moreover, a synopsis table is employed with MAP estimation to decide the temporal locations of the incoming foreground objects in the synopsis video without needing an optimization procedure. As a result, the computational complexity of the proposed video synopsis generation method can be significantly reduced. Furthermore, as it does not require prescreening the entire video, this approach can be applied on online streaming videos.

The exponential growth of surveillance videos presents an unprecedented challenge for high-efficiency surveillance video coding technology. Compared with the existing coding standards that were basically developed for generic videos, surveillance video coding should be designed to make the best use of the special characteristics of surveillance videos (e.g., relative static background). To do so, this paper first conducts two analyses on how to improve the background and foreground prediction efficiencies in surveillance video coding. Following the analysis results, we propose a background-modeling-based adaptive prediction (BMAP) method. In this method, all blocks to be encoded are firstly classified into three categories. Then, according to the category of each block, two novel inter predictions are selectively utilized, namely, the background reference prediction (BRP) that uses the background modeled from the original input frames as the long-term reference and the background difference prediction (BDP) that predicts the current data in the background difference domain. For background blocks, the BRP can effectively improve the prediction efficiency using the higher quality background as the reference; whereas for foreground-background-hybrid blocks, the BDP can provide a better reference after subtracting its background pixels. Experimental results show that the BMAP can achieve at least twice the compression ratio on surveillance videos as AVC (MPEG-4 Advanced Video Coding) high profile, yet with a slightly additional encoding complexity. Moreover, for the foreground coding performance, which is crucial to the subjective quality of moving objects in surveillance videos, BMAP also obtains remarkable gains over several state-of-the-art methods.

H.264/advanced video coding surveillance video encoders use the Skip mode specified by the standard to reduce bandwidth. They also use multiple frames as reference for motion-compensated prediction. In this paper, we propose two techniques to reduce the bandwidth and computational cost of static camera surveillance video encoders without affecting detection and recognition performance. A spatial sampler is proposed to sample pixels that are segmented using a Gaussian mixture model. Modified weight updates are derived for the parameters of the mixture model to reduce floating point computations. A storage pattern of the parameters in memory is also modified to improve cache performance. Skip selection is performed using the segmentation results of the sampled pixels. The second contribution is a low computational cost algorithm to choose the reference frames. The proposed reference frame selection algorithm reduces the cost of coding uncovered background regions. We also study the number of reference frames required to achieve good coding efficiency. Distortion over foreground pixels is measured to quantify the performance of the proposed techniques. Experimental results show bit rate savings of up to 94.5% over methods proposed in literature on video surveillance data sets. The proposed techniques also provide up to 74.5% reduction in compression complexity without increasing the distortion over the foreground regions in the video sequence.

Unmanned Aerial Systems (UAS) have raised a great concern on privacy recently. A practical method to protect privacy is needed for adopting UAS in civilian airspace. This paper examines the privacy policies, filtering strategies, existing techniques, then proposes a novel method based on the encrypted video stream and the cloud-based privacy servers. In this scheme, all video surveillance images are initially encrypted, then delivered to a privacy server. The privacy server decrypts the video using the shared key with the camera, and filters the image according to the privacy policy specified for the surveyed region. The sanitized video is delivered to the surveillance operator or anyone on the Internet who is authorized. In a larger system composed of multiple cameras and multiple privacy servers, the keys can be distributed using Kerberos protocol. With this method the privacy policy can be changed on demand in real-time and there is no need for a costly on-board processing unit. By utilizing the cloud-based servers, advanced image processing algorithms and new filtering algorithms can be applied immediately without upgrading the camera software. This method is cost-efficient and promotes video sharing among multiple subscribers, thus it can spur wide adoption.

Modern military forces are enabled by networked command and control systems, which provide an important interface between the cyber environment, electronic sensors and decision makers. However these systems are vulnerable to cyber attack. A successful cyber attack could compromise data within the system, leading to incorrect information being utilized for decisions with potentially catastrophic results on the battlefield. Degrading the utility of a system or the trust a decision maker has in their virtual display may not be the most effective means of employing offensive cyber effects. The coordination of cyber and kinetic effects is proposed as the optimal strategy for neutralizing an adversary's C4ISR advantage. However, such an approach is an opportunity cost and resource intensive. The adversary's cyber dependence can be leveraged as a means of gaining tactical and operational advantage in combat, if a military force is sufficiently trained and prepared to attack the entire information network. This paper proposes a research approach intended to broaden the understanding of the relationship between command and control systems and the human decision maker, as an interface for both cyber and kinetic deception activity.

Wireless sensor and actuator networks (WSAN) constitute an emerging technology with multiple applications in many different fields. Due to the features of WSAN (dynamism, redundancy, fault tolerance, and self-organization), this technology can be used as a supporting technology for the monitoring of critical infrastructures (CIs). For decades, the monitoring of CIs has centered on supervisory control and data acquisition (SCADA) systems, where operators can monitor and control the behavior of the system. The reach of the SCADA system has been hampered by the lack of deployment flexibility of the sensors that feed it with monitoring data. The integration of a multihop WSAN with SCADA for CI monitoring constitutes a novel approach to extend the SCADA reach in a cost-effective way, eliminating this handicap. However, the integration of WSAN and SCADA presents some challenges which have to be addressed in order to comprehensively take advantage of the WSAN features. This paper presents a solution for this joint integration. The solution uses a gateway and a Web services approach together with a Web-based SCADA, which provides an integrated platform accessible from the Internet. A real scenario where this solution has been successfully applied to monitor an electrical power grid is presented.