Biblio

Currently, one method to deal with the storage and computation of multimedia retrieval applications is an approximate nearest neighbor (ANN) search. Hashing algorithms and Vector quantization (VQ) are widely used in ANN search. So, K-mean clustering is a method of VQ that can solve those problems. With the increasing growth of multimedia data such as text view, image view, video view, audio view, and 3D view. Thus, it is a reason that why multimedia retrieval is very important. We can retrieve the results of each media type by inputting a query of that type. Even though many hashing algorithms and VQ techniques are proposed to produce a compact or short binary codes. In the real-time purposes the exhaustive search is impractical, and Hamming distance computation in the Hamming space suffers inaccurate results. The challenge of this paper is focusing on how to learn multimedia raw data or features representation to search on each media type for multimedia retrieval. So we propose a new search method that utilizes K-mean hash codes by computing the probability of a cluster in the index code. The proposed employs the index code from the K-mean cluster number that is converted to hash code. The inverted index table is constructed basing on the K-mean hash code. Then we can improve the original K-mean index accuracy and efficiency by learning a deep neural network (DNN). We performed the experiments on four benchmark multimedia datasets to retrieve each view such as 3D, image, video, text, and audio, where hash codes are produced by K-mean clustering methods. Our results show the effectiveness boost the performance on the baseline (exhaustive search).

Security preservation is considered as one of the major concerns in this digital world, mainly for performing any online transactions. As the time progress, it witnesses an enormous amount of security threats and stealing different kind of digital information over the online network. In this regard, lots of cryptographic algorithms based on secret key generation techniques have been implemented to boost up the security aspect of network systems that preserve the confidentiality of digital information. Despite this, intelligent intruders are still able to crack the key generation technique, thus stealing the data. In this research article, we propose an innovative approach for generating a pseudo-pseudo-random key sequence that serves as a base for the encryption/decryption process. The key generation process is carried out by extracting the essential features from a facial image and based on the extracted features; a pseudo-random key sequence that acts as a primary entity for the efficient encryption/decryption process is generated. Experimental findings related to the pseudo-random key is validated through chi-square, runs up-down and performs a period of subsequence test. Outcomes of these have subsequently passed in achieving an ideal key.

In this ever updating digitalized world, everything is connected with just few touches away. Our phone is connected with things around us, even we can see live video of our home, shop, institute or company on the phone. But we can't track suspicious activity 24*7 hence needed a smart system to track down any suspicious activity taking place, so it automatically notifies us before any robbery or dangerous activity takes place. We have proposed a framework to tackle down this security matter with the help of sensors enabled cameras(IoT) connected through a FOG layer hence called FOGIoT which consists of small servers configured with Human Activity Analysis Algorithm. Any suspicious activity analyzed will be reported to responsible personnel and the due action will be taken place.

Anomaly detection is critically important for intelligent surveillance systems to detect in a timely manner any malicious activities. Many video anomaly detection approaches using deep learning methods focus on a single camera video stream with a fixed scenario. These deep learning methods use large-scale training data with large complexity. As a solution, in this paper, we show how to use pre-trained convolutional neural net models to perform feature extraction and context mining, and then use denoising autoencoder with relatively low model complexity to provide efficient and accurate surveillance anomaly detection, which can be useful for the resource-constrained devices such as edge devices of the Internet of Things (IoT). Our anomaly detection model makes decisions based on the high-level features derived from the selected embedded computer vision models such as object classification and object detection. Additionally, we derive contextual properties from the high-level features to further improve the performance of our video anomaly detection method. We use two UCSD datasets to demonstrate that our approach with relatively low model complexity can achieve comparable performance compared to the state-of-the-art approaches.

Proof of integrity in produced video data by surveillance cameras requires active forensic methods such as signatures, otherwise authenticity and integrity can be comprised and data becomes unusable e. g. for legal evidence. But a simple file- or stream-signature loses its validity when the stream is cut in parts or by separating data and signature. Using the principles of security in distributed systems similar to those of blockchain and distributed ledger technologies (BC/DLT), a chain which consists of the frames of a video which frame hash values will be distributed among a camera sensor network is presented. The backbone of this Framechain within the camera sensor network will be a camera identity concept to ensure accountability, integrity and authenticity according to the extended CIA triad security concept. Modularity by secure sequences, autarky in proof and robustness against natural modulation of data are the key parameters of this new approach. It allows the standalone data and even parts of it to be used as hard evidence.

A variety of architectures have been designed or repurposed for the task of facial forgery detection. While many of these designs have seen great success, they largely fail to address challenges these models may face in practice. A major challenge is posed by generality, wherein models must be prepared to perform in a variety of domains. In this paper, we investigate the ability of state-of-the-art facial forgery detection architectures to generalize. We first propose two criteria for generality: reliably detecting multiple spoofing techniques and reliably detecting unseen spoofing techniques. We then devise experiments which measure how a given architecture performs against these criteria. Our analysis focuses on two state-of-the-art facial forgery detection architectures, MesoNet and XceptionNet, both being convolutional neural networks (CNNs). Our experiments use samples from six state-of-the-art facial forgery techniques: Deepfakes, Face2Face, FaceSwap, GANnotation, ICface, and X2Face. We find MesoNet and XceptionNet show potential to generalize to multiple spoofing techniques but with a slight trade-off in accuracy, and largely fail against unseen techniques. We loosely extrapolate these results to similar CNN architectures and emphasize the need for better architectures to meet the challenges of generality.

An image forgery method called Deepfakes can cause security and privacy issues by changing the identity of a person in a photo through the replacement of his/her face with a computer-generated image or another person's face. Therefore, a new challenge of detecting Deepfakes arises to protect individuals from potential misuses. Many researchers have proposed various binary-classification based detection approaches to detect deepfakes. However, binary-classification based methods generally require a large amount of both real and fake face images for training, and it is challenging to collect sufficient fake images data in advance. Besides, when new deepfakes generation methods are introduced, little deepfakes data will be available, and the detection performance may be mediocre. To overcome these data scarcity limitations, we formulate deepfakes detection as a one-class anomaly detection problem. We propose OC-FakeDect, which uses a one-class Variational Autoencoder (VAE) to train only on real face images and detects non-real images such as deepfakes by treating them as anomalies. Our preliminary result shows that our one class-based approach can be promising when detecting Deepfakes, achieving a 97.5% accuracy on the NeuralTextures data of the well-known FaceForensics++ benchmark dataset without using any fake images for the training process.

Video Surveillance plays a pivotal role in today's world. The technologies have been advanced too much when artificial intelligence, machine learning and deep learning pitched into the system. Using above combinations, different systems are in place which helps to differentiate various suspicious behaviors from the live tracking of footages. The most unpredictable one is human behaviour and it is very difficult to find whether it is suspicious or normal. Deep learning approach is used to detect suspicious or normal activity in an academic environment, and which sends an alert message to the corresponding authority, in case of predicting a suspicious activity. Monitoring is often performed through consecutive frames which are extracted from the video. The entire framework is divided into two parts. In the first part, the features are computed from video frames and in second part, based on the obtained features classifier predict the class as suspicious or normal.

The challenge of network traffic classification exists at the heart of many networking related tasks aimed at improving the overall user experience and usability of the internet. Current techniques, such as deep packet inspection, depend heavily on interaction by network administrators and engineers to maintain up to date stores of application network signatures and the infrastructure required to utilize them effectively. In this paper, we introduce Network Traffic Images, a 2-dimensional (2D) formulation of a stream of packet header lengths, which enable us to employ deep convolutional neural networks for network traffic classification. Five different network traffic image orientation mappings are carefully designed to deduce the best way to transform the 1-dimensional packet-subflow into a 2D image. Two different mapping strategies, one packet-relative and the other time-relative, are experimented with to map the packets of a packet flow to the pixels in the image. Experiments shows that high classification accuracy can be achieved with minimal manual effort using network traffic images in deep learning.

Re-drawing the image as a certain artistic style is considered to be a complicated task for computer machine. On the contrary, human can easily master the method to compose and describe the style between different images. In the past, many researchers studying on the deep neural networks had found an appropriate representation of the artistic style using perceptual loss and style reconstruction loss. In the previous works, Gatys et al. proposed an artificial system based on convolutional neural networks that creates artistic images of high perceptual quality. Whereas in terms of running speed, it was relatively time-consuming, thus it cannot apply to video style transfer. Recently, a feed-forward CNN approach has shown the potential of fast style transformation, which is an end-to-end system without hundreds of iteration while transferring. We combined the benefits of both approaches, optimized the feed-forward network and defined time loss function to make it possible to implement the style transfer on video in real time. In contrast to the past method, our method runs in real time with higher resolution while creating competitive visually pleasing and temporally consistent experimental results.

With the rapid development of the Internet of vehicles, there is a huge amount of multimedia data becoming a hidden trouble in the Internet of Things. Therefore, it is necessary to process and store them in real time as a way of big data curation. In this paper, a method of real-time processing and storage based on CDN in vehicle monitoring system is proposed. The MPEG-DASH standard is used to process the multimedia data by dividing them into MPD files and media segments. A real-time monitoring system of vehicle on the basis of the method introduced is designed and implemented.

The goal of this work was to identify and try to solve some of the vulnerabilities present in the AR Drone 2.0 by Parrot. The approach was to identify how the system worked, find and analyze vulnerabilities and flaws in the system as a whole and in the software, and find solutions to those problems. Analyzing the results of some tests showed that the system has an open WiFi network and the communication between the controller and the drone are unencrypted. Analyzing the Linux operating system that the drone uses, we see that "Pairing Mode" is the only way the system protects itself from unauthorized control. This is a feature that can be easily bypassed. Port scans reveal that the system has all the ports for its services open and exposed. This makes it susceptible to attacks like DoS and takeover. This research also focuses on some of the software vulnerabilities, such as Busybox that the drone runs. Lastly, this paper discuses some of the possible methods that can be used to secure the drone. These methods include securing the messages via SSH Tunnel, closing unused ports, and re-implementing the software used by the drone and the controller.

Cyber-physical systems are an integral component of weapons, sensors and autonomous vehicles, as well as cyber assets directly supporting tactical forces. Mission resilience of tactical networks affects command and control, which is important for successful military operations. Traditional engineering methods for mission assurance will not scale during battlefield operations. Commanders need useful mission resilience metrics to help them evaluate the ability of cyber assets to recover from incidents to fulfill mission essential functions. We develop 6 cyber resilience metrics for tactical network architectures. We also illuminate how psychometric modeling is necessary for future research to identify resilience metrics that are both applicable to the dynamic mission state and meaningful to commanders and planners.

We formulate a tracker which performs incessant decision making in order to track objects where the objects may undergo different challenges such as partial occlusions, moving camera, cluttered background etc. In the process, the agent must make a decision on whether to keep track of the object when it is occluded or has moved out of the frame temporarily based on its prediction from the previous location or to reinitialize the tracker based on the belief that the target has been lost. Instead of the heuristic methods we depend on reward and penalty based training that helps the agent reach an optimal solution via this partially observable Markov decision making (POMDP). Furthermore, we employ deeply learned compositional model to estimate human pose in order to better handle occlusion without needing human inputs. By learning compositionality of human bodies via deep neural network the agent can make better decision on presence of human in a frame or lack thereof under occlusion. We adapt skeleton based part representation and do away with the large spatial state requirement. This especially helps in cases where orientation of the target in focus is unorthodox. Finally we demonstrate that the deep reinforcement learning based training coupled with pose estimation capabilities allows us to train and tag multiple large video datasets much quicker than previous works.

This paper reports the definition, setup and obtained results of the Fed4FIRE + medium experiment ERASER, aimed to evaluate the actual Quality of Service (QoS) guarantees that the clean-slate Recursive InterNetwork Architecture (RINA) can deliver to heterogeneous applications at large-scale. To this goal, a 37-Node 5G metro/regional RINA network scenario, spanning from the end-user to the server where applications run in a datacenter has been configured in the Virtual Wall experimentation facility. This scenario has initially been loaded with synthetic application traffic flows, with diverse QoS requirements, thus reproducing different network load conditions. Next,their experienced QoS metrics end-to-end have been measured with two different QTA-Mux (i.e., the most accepted candidate scheduling policy for providing RINA with its QoS support) deployment scenarios. Moreover, on this RINA network scenario loaded with synthetic application traffic flows, a real HD (1080p) video streaming demonstration has also been conducted, setting up video streaming sessions to end-users at different network locations, illustrating the perceived Quality of Experience (QoE). Obtained results in ERASER disclose that, by appropriately deploying and configuring QTA-Mux, RINA can yield effective QoS support, which has provided perfect QoE in almost all locations in our demo when assigning video traffic flows the highest (i.e., Gold) QoS Cube.

Nowadays, multimedia content retrieval has become the major service requirement of the Internet and the traffic of these contents has dominated the IP traffic. To reduce the duplicated traffic and improve the performance of distributing massive volumes of multimedia contents, in-network caching has been proposed recently. However, because in-network content caching can be directly utilized to respond users' requests, multimedia content retrieval is beyond content providers' control and makes it hard for them to implement access control and service accounting. In this paper, we propose an attribute-based accountable access control scheme for multimedia content distribution while making the best of in-network caching, in which content providers can be fully offline. In our scheme, the attribute-based encryption at multimedia content provider side and access policy based authentication at the edge router side jointly ensure the secure access control, which is also efficient in both space and time. Besides, secure service accounting is implemented by letting edge routers collect service credentials generated during users' request process. Through the informal security analysis, we prove the security of our scheme. Simulation results demonstrate that our scheme is efficient with acceptable overhead.

Media streaming has largely dominated the Internet traffic and the trend will keep increasing in the next years. To efficiently distribute the media content, Information-Centric Networking (ICN) has attracted many researchers. Since end users usually obtain content from indeterminate caches in ICN, the publisher cannot reinforce data security and access control depending on the caches. Hence, the ability of self-contained protection is important for the cached contents. Attribute-based encryption (ABE) is considered the preferred solution to achieve this goal. However, the existing ABE schemes usually have problems regarding efficiency. The exponentiation in key generation and pairing operation in decryption respectively increases linearly with the number of attributes involved, which make it costly. In this paper, we propose an efficient key-policy ABE with fast key generation and decryption (FKP-ABE). In the key generation, we get rid of exponentiation and only require multiplications/divisions for each attribute in the access policy. And in the decryption, we reduce the pairing operations to a constant number, no matter how many attributes are used. The efficiency analysis indicates that our scheme has better performance than the existing KP-ABE schemes. Finally, we present an implementation framework that incorporates the proposed FKP-ABE with the ICN architecture.

ASA systems (firewall, IDS, IPS) are probable to become communication bottlenecks in networks with growing network bandwidths. To alleviate this issue, we suggest to use Application-aware mechanism based on Deep Packet Inspection (DPI) to bypass chosen traffic around firewalls. The services of Internet video sharing gained importance and expanded their share of the multimedia market. The Internet video should meet strict service quality (QoS) criteria to make the broadcasting of broadcast television a viable and comparable level of quality. However, since the Internet video relies on packet communication, it is subject to delays, transmission failures, loss of data and bandwidth restrictions that may have a catastrophic effect on the quality of multimedia.

In recent years, developments in the field of computer vision have allowed deep learning-based techniques to surpass human-level performance. However, these advances have also culminated in the advent of adversarial machine learning techniques, capable of launching targeted image captioning attacks that easily fool deep learning models. Although attacks in the image domain are well studied, little work has been done in the video domain. In this paper, we show it is possible to extend prior attacks in the image domain to the video captioning task, without heavily affecting the video's playback quality. We demonstrate our attack against a state-of-the-art video captioning model, by extending a prior image captioning attack known as Show and Fool. To the best of our knowledge, this is the first successful method for targeted attacks against a video captioning model, which is able to inject 'subliminal' perturbations into the video stream, and force the model to output a chosen caption with up to 0.981 cosine similarity, achieving near-perfect similarity to chosen target captions.

Vehicular Named Data Network (VNDN) uses Named Data Network (NDN) as a communication enabler. The communication is achieved using the content name instead of the host address. NDN integrates content caching at the network level rather than the application level. Hence, the network becomes aware of content caching and delivering. The content caching is a fundamental element in VNDN communication. However, due to the limitations of the cache store, only the most used content should be cached while the less used should be evicted. Traditional caching replacement policies may not work efficiently in VNDN due to the large and diverse exchanged content. To solve this issue, we propose an efficient cache replacement policy that takes the quality of service into consideration. The idea consists of classifying the traffic into different classes, and split the cache store into a set of sub-cache stores according to the defined traffic classes with different storage capacities according to the network requirements. Each content is assigned a popularity-density value that balances the content popularity with its size. Content with the highest popularity-density value is cached while the lowest is evicted. Simulation results prove the efficiency of the proposed solution to enhance the overall network quality of service.

We consider a cloud based multiserver system consisting of a set of replica application servers behind a set of proxy (indirection) servers which interact directly with clients over the Internet. We study a proactive moving-target defense to thwart a DDoS attacker's reconnaissance phase and consequently reduce the attack's impact. The defense is effectively a moving-target (motag) technique in which the proxies dynamically change. The system is evaluated using an AWS prototype of HTTP redirection and by numerical evaluations of an “adversarial” coupon-collector mathematical model, the latter allowing larger-scale extrapolations.

In this paper, we propose a video surveillance system based on blockchain system. The proposed system consists of a blockchain network with trusted internal managers. The metadata of the video is recorded on the distributed ledger of the blockchain, thereby blocking the possibility of forgery of the data. The proposed architecture encrypts and stores the video, creates a license within the blockchain, and exports the video. Since the decryption key for the video is managed by the private DB of the blockchain, it is not leaked by the internal manager unauthorizedly. In addition, the internal administrator can manage and export videos safely by exporting the license generated in the blockchain to the DRM-applied video player.

Video surveillance system is an important application system on the ubiquitous SG-eIoT. A comparative analysis of the traditional video surveillance scheme and the unified video surveillance solution in the eIoT environment is made. Network load and service latency parameters under the two schemes are theoretically modeled and simulated. Combined with the simulation results, the corresponding suggestions for the access of video terminals in the ubiquitous eIoT are given.

In view of the challenges with Aids to Navigation (AtoN) managements and emergency response, the present study designs and presents an AtoN real-time video surveillance system based on the AIS collision warning. The key technologies regarding with AtoN cradle head control and testing algorithms, video image fusion, system operation and implementation are demonstrated in details. Case study is performed at Guan River (China) to verify the effectiveness of the AtoN real-time video surveillance system for maritime security supervision. The research results indicate that the intellective level of the AtoN maintenance and managements could be significantly improved. The idea of designing modules brings a good flexibility and a high portability for the present surveillance system, therefore provides a guidance for the design of similar maritime surveillance systems.

Recently, Pan/Tilt/Zoom (PTZ) camera has been widely used in video surveillance systems. However, it is difficult to automatically control PTZ cameras according to moving objects in the surveillance area. This paper proposes an automatic camera control method based on a Deep-Q Network (DQN) for improving the recognition accuracy of anomaly actions in the video surveillance system. To generate PTZ camera control values, the proposed method uses the position and size information of the object which received from the video analysis system. Through implementation results, the proposed method can automatically control the PTZ camera according to moving objects.