The generative adversarial network (GAN) aims to approximate an unknown distribution via a parameterized neural network (NN). While GANs have been widely applied in reinforcement and semi-supervised learning as well as computer vision tasks, selecting their parameters often needs an exhaustive search and only a few selection methods can be proved to be theoretically optimal. One of the most promising GAN variants is the Wasserstein GAN (WGAN). Prior work on optimal parameters for WGAN is limited to the linear-quadratic-Gaussian (LQG) setting, where the NN is linear and the data is Gaussian. In this paper, we focus on the characterization of optimal WGAN parameters beyond the LQG setting. We derive closed-form optimal parameters for one-dimensional WGANs with non-linear sigmoid and ReLU activation functions. Extensions to high-dimensional WGANs are also discussed. Empirical studies show that our closed-form WGAN parameters have good convergence behavior with data under both Gaussian and Laplace distributions.

Massive open online courses (MOOCs) have high potential for improving education worldwide, but understanding of student behavior and situations is difficult to achieve in online settings. Network analytics and visualizations can assist instructors with supporting understanding of student behavior as courses unfold. In this work, we perform a visual comparative analysis of two different MOOC courses to analyze the impacts of course structure differences and demonstrate the benefits of visual network analysis in this context. We present several insights: (1) behavior features that are best for prediction of student attrition varied with course structure, (2) a large proportion (about 35%) of students never received a reply to their original post and this was correlated with an eventual dropout, and (3) students that received a reply to their original post were twice as likely to post again. We contribute several information visualizations of student network data and draw recommendations for MOOC instructors and designers of course systems.

Users with anomalous behaviors in online communication systems (e.g. email and social medial platforms) are potential threats to society. Automated anomaly detection based on advanced machine learning techniques has been developed to combat this issue; challenges remain, though, due to the difficulty of obtaining proper ground truth for model training and evaluation. Therefore, substantial human judgment on the automated analysis results is often required to better adjust the performance of anomaly detection. Unfortunately, techniques that allow users to understand the analysis results more efficiently, to make a confident judgment about anomalies, and to explore data in their context, are still lacking. In this paper, we propose a novel visual analysis system, TargetVue, which detects anomalous users via an unsupervised learning model and visualizes the behaviors of suspicious users in behavior-rich context through novel visualization designs and multiple coordinated contextual views. Particularly, TargetVue incorporates three new ego-centric glyphs to visually summarize a user's behaviors which effectively present the user's communication activities, features, and social interactions. An efficient layout method is proposed to place these glyphs on a triangle grid, which captures similarities among users and facilitates comparisons of behaviors of different users. We demonstrate the power of TargetVue through its application in a social bot detection challenge using Twitter data, a case study based on email records, and an interview with expert users. Our evaluation shows that TargetVue is beneficial to the detection of users with anomalous communication behaviors.

In this paper, we develop a pipelining schema for image deep learning on GPU cluster to leverage heavy workload of training procedure. In addition, it is usually necessary to train multiple models to obtain a good deep learning model due to the limited a priori knowledge on deep neural network structure. Therefore, adopting parallel and distributed computing appears is an obvious path forward, but the mileage varies depending on how amenable a deep network can be parallelized and the availability of rapid prototyping capabilities with low cost of entry. In this work, we propose a framework to organize the training procedures of multiple deep learning models into a pipeline on a GPU cluster, where each stage is handled by a particular GPU with a partition of the training dataset. Instead of frequently migrating data among the disks, CPUs, and GPUs, our framework only moves partially trained models to reduce bandwidth consumption and to leverage the full computation capability of the cluster. In this paper, we deploy the proposed framework on popular image recognition tasks using deep learning, and the experiments show that the proposed method reduces overall training time up to dozens of hours compared to the baseline method.

Understanding how human emotion is evoked from visual content is a task that we as people do every day, but machines have not yet mastered. In this work we address the problem of predicting the intended evoked emotion at given points within movie trailers. Movie Trailers are carefully curated to elicit distinct and specific emotional responses from viewers, and are therefore well-suited for emotion prediction. However, current emotion recognition systems struggle to bridge the "affective gap", which refers to the difficulty in modeling high-level human emotions with low-level audio and visual features. To address this problem, we propose a mid-level concept feature, which is based on detectable movie shot concepts which we believe to be tied closely to emotions. Examples of these concepts are "Fight", "Rock Music", and "Kiss". We also create 2 datasets, the first with shot-level concept annotations for learning our concept detectors, and a separate, second dataset with emotion annotations taken throughout the trailers using the two dimensional arousal and valence model for emotion annotation. We report the performance of our concept detectors, and show that by using the output of these detectors as a mid-level representation for the movie shots we are able to more accurately predict the evoked emotion throughout a trailer than by using low-level features.

Utilizing channel reciprocity, the traditional time-reversal technique boosts the signal-to-noise ratio at the receiver with very low transmitter complexity. However, the large delay spread gives rise to severe inter-symbol interference (ISI) when the data rate is high, and the achievable transmission rate is further degraded in the multiuser downlink due to the inter-user interference (IUI). In this work, we study the weighted sum rate optimization problem by means of waveform design in the time-reversal multiuser downlink where the receiver processing is based on a single sample. Power allocation has a significant impact on the waveform design problem. We propose a new power allocation algorithm named Iterative SINR Waterfilling, which is able to achieve comparable sum rate performance to that of globally optimal power allocation. We further propose another approach called Iterative Power Waterfilling for multiple data streams. Iterative SINR Waterfilling provides better performance than Iterative Power Waterfilling in the scenario of high interference, while Iterative Power Waterfilling can work under multiple data streams. Simulation results show the superior performance of the proposed algorithms in comparison with other waveform designs such as zero-forcing and conventional time-reversal waveform.

Due to the ease with which digital images can be forged, a great deal of work has been done in the field of digital image forensics. A particularly important problem is to forensically determine an image's acquisition and storage history. Recent research has shown that a new acquisition technique known as compressive sensing can be used to capture a digital image. Images acquired by compressive sensing can not be easily forensically distinguished from the images captured using standard digital cameras, nor from those which have undergone Discrete Wavelet Transform (DWT) based compressions. In this paper, we propose a two step detection scheme to identify the images acquired by compressive sensing. The first step identifies unaltered images captured using standard digital cameras and the second step separates compressively sensed images from ones compressed using DWT-based techniques. Our simulations show the first step of detection can achieve a probability of detection (Pd) of 100% for probability of false alarm (Pf) less than 4%, and the second step gets Pdnearly 90% with Pfof 10%.

This paper presents a game-theoretical approach to provide a framework for optimal template selection in image prediction. Image prediction is an effective tool for coding still images and intra pictures in videos. Template matching algorithms which use neighboring blocks of the prediction target as templates have been widely used for image prediction. The assumption of these approaches is that the template has similar textural structures as the prediction target. Up to now these approaches all use pre-fixed templates for all prediction targets. However, in real images, these fixed templates are very likely to contain textures that are not or are not significant in the prediction targets and these insignificant textures introduce larger prediction residues. In this paper, we propose a coalitional game in which every pixel is treated as a player and tries to seek partners to form a coalition to capture the textural structure. By forming a coalition, every player in the coalition can obtain a gain of improving the ability of capturing the textural structure of coalition while incurring a cost of introducing textural variance within the coalition. Experimental results show that the proposed game-theoretical approach outperforms the conventional pre-fixed template matching prediction up to 2dB coding gain.

In order to combat the spread of digital forgeries, researchers have developed a variety of forensic techniques to verify the authenticity of digital multimedia files. Though many of these techniques can reliably detect traditional forgeries, recent research has shown that they can easily be fooled by anti-forensic operations designed to hide evidence of forgery. In response, new forensic techniques have been developed to detect the use of anti-forensics. In light of this, there is now a need to develop a theoretical understanding of the interactions between a forger using anti-forensics and a forensic investigator. In this paper, we propose techniques to evaluate the performance of anti-forensic algorithms along with a game theoretic framework for analyzing the interplay between forensics and anti-forensics. Furthermore, we propose a new automatic video frame deletion detection technique along with a technique to detect the use of video anti-forensics. We evaluate these techniques using our proposed analytical framework.

While demand response has achieved promising results on making the power grid more efficient and reliable, the additional dynamics and flexibility brought by demand response also increase the uncertainty and complexity of the centralized load forecast. In this paper, we propose a game theoretic demand response scheme that can transform the traditional centralized load prediction structure into a distributed load prediction system by the participation of customers. Moreover, since customers are generally rational and thus naturally selfish, they may cheat if cheating can improve their payoff. Therefore, enforcing truth-telling is crucial. We prove analytically and demonstrate with simulations that the proposed game theoretic scheme is cheat-proof, i.e., all customers are motivated to report and consume their true optimal demands and any deviation will lead to a utility loss. We also prove theoretically that the proposed demand response scheme can lead to the solution that maximizes social welfare and is proportionally fair in terms of utility function. Moreover, we propose a simple dynamic pricing algorithm for the power substation to control the total demand of all customers to meet the target demand curve. Finally, simulations are shown to demonstrate the efficiency and effectiveness of the proposed game theoretic algorithm.

The rising cost of energy and increased environmental awareness have sparked a keen interest in the development and deployment of energy-efficient communication technologies. The energy efficiency of cellular networks can be increased significantly by selectively switching off some of the base stations (BSs) during periods of low traffic load. In this paper, we propose a scalable BS switching strategy and use cooperative communications and power control to extend network coverage to the service areas of the switched-off BSs. The outage probability and the achievable power savings of the proposed scheme are analyzed, both analytically and numerically, and a potential of up to 50% power saving is observed in the numerical results.

We formulate the wireless security problem as an indirect reciprocity game, and propose a security mechanism that applies the indirect reciprocity principle to suppress attacks in wireless networks. In this system, a large number of nodes cooperate to reject the network access requests from attackers during the punishment periods. If the punishment time is so long that the cost due to the loss of network services exceeds the illegal security gains of the attack, rational nodes do not have incentive to attack, and hence our system can reduce the attacking probability in the network. We develop a social norm and reputation updating process to build such an indirect reciprocity mechanism for the network. We evaluate the evolutionarily stable strategy (ESS) in the game, and provide the optimal action strategy and its corresponding stationary reputation distribution. Our system is robust against collusion attacks, and can significantly reduce the attacking rate for a wide range of attacks. Simulation results show that our system has much better security performance than the direct reciprocity mechanism, especially in the large-scale wireless network with terminal mobility. Our system can be applied to many wireless networks including cognitive radio networks to improve their security performance.

Due to the ease with which digital information can be altered, many digital forensic techniques have been developed to authenticate multimedia content. Similarly, a number of anti-forensic operations have recently been designed to make digital forgeries undetectable by forensic techniques. However, like the digital manipulations they are designed to hide, many anti-forensic operations leave behind their own forensically detectable traces. As a result, a digital forger must balance the trade-off between completely erasing evidence of their forgery and introducing new evidence of anti-forensic manipulation. Because a forensic investigator is typically bound by a constraint on their probability of false alarm (P_fa), they must also balance a trade-off between the accuracy with which they detect forgeries and the accuracy with which they detect the use of anti-forensics. In this paper, we analyze the interaction between a forger and a forensic investigator by examining the problem of authenticating digital videos. Specifically, we study the problem of adding or deleting a sequence of frames from a digital video. We begin by developing a theoretical model of the forensically detectable fingerprints that frame deletion or addition leaves behind, then use this model to improve upon the video frame deletion or addition detection technique proposed by Wang and Farid. Next, we propose an anti-forensic technique designed to fool video forensic techniques and develop a method for detecting the use of anti-forensics. We introduce a new set of techniques for evaluating the performance of anti-forensic operations and develop a game theoretic framework for analyzing the interplay between a forensic investigator and a forger. We use these new techniques to evaluate the performance of each of our proposed forensic and anti-forensic techniques, and identify the optimal actions of both the forger and forensic investigator.

Radio nodes can obtain illegal security gains by performing attacks, and they are motivated to do so if the illegal gains are larger than the resulting costs. Most existing direct reciprocity-based works assume constant interaction among players, which does not always hold in large-scale networks. In this paper, we propose a security system that applies the indirect reciprocity principle to combat attacks in wireless networks. Because network access is highly desirable for most nodes, including potential attackers, our system punishes attackers by stopping their network services. With a properly designed social norm and reputation updating process, the aim is to incur a cost due to the loss of network access to exceed the illegal security gain. Thus rational nodes are motivated to abandon adversary behavior for their own interests. We derive the optimal strategy and the corresponding stationary reputation distribution, and evaluate the stability condition of the optimal strategy using the evolutionarily stable strategy concept. This security system is robust against collusion attacks and can significantly reduce the attacker population for a wide range of attacks when the stability condition is satisfied. Simulation results show that the proposed system significantly outperforms the existing direct reciprocity-based systems, especially in the large-scale networks with terminal mobility. This technique can be extended to many wireless networks, including cognitive radio networks, to improve their security performance.

Mobile phones are among the most popular consumer devices, and the recent developments of 3G networks and smart phones enable users to watch video programs by subscribing data plans from service providers. Due to the ubiquity of mobile phones and phone-to-phone communication technologies, data-plan subscribers can redistribute the video content to nonsubscribers. Such a redistribution mechanism is a potential competitor for the mobile service provider and is very difficult to trace given users' high mobility. The service provider has to set a reasonable price for the data plan to prevent such unauthorized redistribution behavior to protect or maximize his/her own profit. In this paper, we analyze the optimal price setting for the service provider by investigating the equilibrium between the subscribers and the secondary buyers in the content-redistribution network. We model the behavior between the subscribers and the secondary buyers as a noncooperative game and find the optimal price and quantity for both groups of users. Based on the behavior of users in the redistribution network, we investigate the evolutionarily stable ratio of mobile users who decide to subscribe to the data plan. Such an analysis can help the service provider preserve his/her profit under the threat of the redistribution networks and can improve the quality of service for end users.

Users in multimedia social networks actively interact with each other. It is crucial to study the complex user dynamics and analyze its impact on the performance of multimedia social networks. This paper uses multimedia fingerprinting as an example and studies user dynamics in colluder social networks. During collusion, a group of attackers collectively attack multimedia fingerprinting system and use multimedia content illegally. This paper analyzes the incentives of cooperation among attackers and investigates how colluders form their coalitions to maximize their payoffs. We present a game-theoretic framework to model the complex dynamics among colluders, analyze when attackers cooperate with each other, and investigate how a colluder selects his/her fellow attackers to maximize his/her own payoff. We analyze multiuser collusion in two scenarios: when all attackers receive fingerprinted copies of the same resolution, and when they have copies of different resolutions. The proposed framework considers both the colluders' risk of being detected by the digital rights enforcer and the reward received from illegal usage of multimedia content. Our analysis shows that in both scenarios, colluding with more attackers does not always increase an attacker's utility, and attackers may not always want to cooperate with each other. We first examine the necessary conditions for attackers to collude together, and study how they select the collusion parameters such that cooperation benefits all colluders. We then study how the number of colluders affects each attacker's utility, and investigate the optimum strategy that an attacker should use to select fellow attackers and to form a coalition in order to maximize his or her own payoff.

The recent developments of smart mobile phones and 3G networks enable users to enjoy video programs by subscribing to data plans. Due to phone-to-phone communication technologies and ubiquity of mobile phones, data-plan subscribers are able to redistribute the video content to non-subscribers. Such a redistribution mechanism is a potential competitor for the mobile service provider and is very difficult to trace given users' high mobility. The service provider has to set a reasonable price for the data plan to prevent such unauthorized re-distribution behavior to protect or maximize his/her own profit. In this paper, we investigate the evolutionarily stable ratio of mobile users who decide to subscribe to the data plan. Such an analysis can help the service provider preserve his/her profit under the threat of the redistribution networks and can improve the quality of service for end users.

We present a physical-layer fingerprint-embedding scheme for orthogonal frequency-division-multiplexing (OFDM) transmissions, where the fingerprint signal conveys a low capacity communication suitable for authenticating the transmission and further facilitating secure communications. Our system strives to embed the fingerprint message into the noise subspace of the channel estimates obtained by the receiver, using a number of signal spreading techniques. When side information of the channel state is known and leveraged by the transmitter, the performance of the fingerprint embedding can be improved. When channel state information is not known, blind spreading techniques are applied. The fingerprint message is only visible to aware receivers who explicitly preform detection of the signal, but is invisible to receivers employing typical channel equalization. A taxonomy of overlay designs is discussed and these designs are explored through experiment using time-varying channel-state information (CSI) recorded from IEEE802.16e Mobile WiMax base stations. The performance of the fingerprint signal as received by a WiMax subscriber is demonstrated using CSI measurements derived from the downlink signal. Detection performance for the digital fingerprint message in time-varying channel conditions is also presented via simulation.

Multimedia social network is a network infrastructure in which the social network users share multimedia contents with all different purposes. Analyzing user behavior in multimedia social networks helps design more secured and efficient multimedia and networking systems. Multimedia fingerprinting protects multimedia from illegal alterations and multiuser collusion is a cost-effective attack. The colluder social network is naturally formed during multiuser collusion with which colluders gain reward by redistributing the colluded multimedia contents. Since the colluders have conflicting interest, the maximal-payoff collusion for one colluder may not be the maximal-payoff collusion for others. Hence, before a collusion being successful, the colluders must bargain with each other to reach agreements. We first model the bargaining behavior among colluders as a noncooperative game and study four different bargaining solutions of this game. Moreover, the market value of the redistributed multimedia content is often time-sensitive. The earlier the colluded copy being released, the more the people are willing to pay for it. Thus, the colluders have to reach agreements on how to distribute reward and risk among themselves as soon as possible. This paper further incorporates this time-sensitiveness of the colluders' reward and studies the time-sensitive bargaining equilibrium. The study in this paper reveals the strategies that are optimal for the colluders; thus, all the colluders have no inventive to disagree. Such understanding reduces the possible types of collusion into a small finite set.

Traditional cooperative communications consider dedicated-relays, while often such relays may not be available. In this paper, we consider wireless transceivers that relay signals in addition to their own primary communication mission. We consider a best-effort delivery policy, where a node is not obligated to devote energy to cooperatively relay signals, nor does it provide a guarantee of signal quality on retransmissions. Instead the relay sacrifices energy at its own discretion, with priority given to the primary communication mission. We consider one best-effort delivery problem: a system that transmits an additional relay signal within its original transmission energy budget while inducing minimal degradation to the primary-user's signal. To maintain this constraint, we consider the feasibility of reallocating energy from pilot signals used for channel estimation toward the relaying service, when channel conditions are stationary. We demonstrate that transmitter energy may be dynamically allocated between a relay component and a pilot component of the transmission using best-effort delivery. This power allocation is critical to system performance, since both the primary-user and the secondary-user may require pilot energy to correctly decode transmitted signals. Sub-optimal power allocation rules with respect to primary-user channel estimate mean-square error and pairwise error probability are derived.

A framework for introducing an extrinsic fingerprint signal to space-time coded transmissions at the physical layer is presented, where the fingerprint signal conveys a low capacity cryptographically secure authentication message of arbitrary length. The multi-bit digital fingerprint message conveyed by the fingerprint signal is available to all users within reception range and is used to authenticate the fingerprinted transmission. A novel approach is discussed where the fingerprint signaling mechanism mimics distortions similar to time-varying channel effects. Specifically, the fingerprint is detectable to receivers considering previous channel state information, but will be ignored by receivers equalizing according to current channel state information. Two example fingerprint signaling mechanisms and detection rules are presented based on pulse-amplitude keying and phase-shift keying approaches. The methods for obtaining the real (intrinsic) channel estimate, the extrinsic fingerprint message, and the primary transmission are analytically demonstrated using general pilot embedding schemes. The worst-case distortions caused by non-ideal equalization of a fingerprinted message are derived using the 2×2 Alamouti code. Simulation results including bit error rate (BER) and model mismatch error using a maximum-likelihood (ML) receiver are presented for both the primary and fingerprint signal, while authentication signal BERs lower than the primary signal are demonstrated.

A framework for introducing an extrinsic fingerprint signal to space-time coded transmissions at the physical-layer is presented, whereby the fingerprint signal conveys a low capacity digital communication suitable for authenticating the transmission and further facilitating secure communications. A novel approach is discussed where the fingerprint signal mimics distortions similar to time-varying channel effects. Specifically, the fingerprint signal is only visible to aware receivers considering previous channel state information (CSI) and is otherwise invisible to a receiver equalizing according to current CSI. An augmented signal is created consisting of the original transmission, or primary message, and the fingerprint message. An example fingerprint signal and detection rule are presented based on a phase-shift keying approach. Simulation results including bit error rate (BER) are presented for both the primary and fingerprint signals using the 2×2 Alamouti code, and authentication signal BERs lower than the primary signal are demonstrated.

Mobile phones are among the most popular consumer devices and the recent developments of 3G networks and smart phones enable users to watch video programs by subscribing data plans from service providers. Due to the ubiquity of mobile phones and phone-to-phone communication technologies, subscribers can redistribute the video content to non-subscribers. Such a redistribution mechanism is a potential competitor for the service provider and is very difficult to trace given the users'' high mobility. The service provider has to set a reasonable price for the data plan to prevent such re-distribution behavior to protect his/her own profit. In this paper, we analyze the optimal price setting for the service provider by investigating the equilibrium between the subscribers and the secondary buyers in the content-redistribution network. We model the behavior between the subscribers and the secondary buyers as a hybrid Stackelburg auction game and find the optimal price and quantity for both groups of users. Such an analysis can help the service provider preserve their profit under the threat of the redistribution networks and can improve the quality of service for end users.

Users using the same video streaming service within a wireless network share the same limited backbone bandwidth to the Internet. These users are motivated to collaborate with each other to obtain better-quality service. The decisions and actions of users influence the performance of others, hence they form a social network. In a fully-distributed wireless network, malicious attack can cause much more damage than over the Internet since the unstable wireless channel allows hostile users to mimic as a non-malicious user. Therefore, a robust attack-resistant cooperation strategy for non-malicious user is needed to combat the challenges in wireless networks. In this paper, we incorporate trust modelling into the cooperation among users to increase attack-resistance. Simulation results show our robust cooperation strategies can against 40% more attackers.

The widespread availability of photo editing software has made it easy to create visually convincing digital image forgeries. To address this problem, there has been much recent work in the field of digital image forensics. There has been little work, however, in the field of anti-forensics, which seeks to develop a set of techniques designed to fool current forensic methodologies. In this work, we present a technique for disguising an image's JPEG compression history. An image's JPEG compression history can be used to provide evidence of image manipulation, supply information about the camera used to generate an image, and identify forged regions within an image. We show how the proper addition of noise to an image's discrete cosine transform coefficients can sufficiently remove quantization artifacts which act as indicators of JPEG compression while introducing an acceptable level of distortion. Simulation results are provided to verify the efficacy of this anti-forensic technique.

Dictionary learning through matrix factorization has become widely popular for performing music transcription and source separation. These methods learn a concise set of dictionary atoms which represent spectrograms of musical objects. However, there is no guarantee that the atoms learned will be perceptually meaningful, particularly when there exists significant spectral and temporal overlap among the musical sources. In this paper, we propose a novel dictionary learning method that imposes additional harmonic constraints upon the atoms of the learned dictionary while allowing the dictionary size to grow appropriately during the learning procedure. When there is significant spectral-temporal overlap among the musical sources, our method outperforms popular existing matrix factorization methods as measured by the recall and precision of learned dictionary atoms.

The wide-spread use of P2P video streaming systems have introduced a large number of unnecessary traverse links leading to substantial network inefficiency. To address this problem and achieve better streaming performance, we propose to enable cooperation among group peers, which are geographically neighboring peers with large intra-group upload and download bandwidths. Considering the peers' selfish nature, we formulate the cooperative streaming problem as an evolutionary game and derive the evolutionarily stable strategy (ESS) for every peer. Moreover, we propose a simple and distributed learning algorithm for the peers to converge to the ESSs. Compared to the traditional non-cooperative P2P schemes, the proposed cooperative scheme achieves much better performance in terms of social welfare and probability of real-time streaming.

Recently, a number of digital image forensic techniques have been developed which are capable of identifying an image's origin, tracing its processing history, and detecting image forgeries. Though these techniques are capable of identifying standard image manipulations, they do not address the possibility that anti-forensic operations may be designed and used to hide evidence of image tampering. In this paper, we propose an anti-forensic operation capable of removing blocking artifacts from a previously JPEG compressed image. Furthermore, we show that by using this operation along with another anti-forensic operation which we recently proposed, we are able to fool forensic methods designed to detect evidence of JPEG compression in decoded images, determine an image's origin, detect double JPEG compression, and identify cut-and-paste image forgeries.

While peer-to-peer (P2P) video streaming systems have achieved promising results, they introduce a large number of unnecessary traverse links, which consequently leads to substantial network inefficiency. To address this problem and achieve better streaming performance, we propose to enable cooperation among “group peers,” which are geographically neighboring peers with large intra-group upload and download bandwidths. Considering the peers' selfish nature, we formulate the cooperative streaming problem as an evolutionary game and derive, for every peer, the evolutionarily stable strategy (ESS), which is the stable Nash equilibrium and no one will deviate from. Moreover, we propose a simple and distributed learning algorithm for the peers to converge to the ESSs. With the proposed algorithm, each peer decides whether to be an agent who downloads data from the peers outside the group or a free-rider who downloads data from the agents by simply tossing a coin, where the probability of being a head for the coin is learned from the peer's own past payoff history. Simulation results show that the strategy of a peer converges to the ESS. Compared to the traditional non-cooperative P2P schemes, the proposed cooperative scheme achieves much better performance in terms of social welfare, probability of real-time streaming, and video quality (source rate).

Copyright protection is a key issue for video sharing over public networks. To protect the video content from unauthorized redistribution, digital fingerprinting is commonly used. To develop an efficient collusion-resistant fingerprinting scheme, it is very important for the system designer to understand how the behavior dynamics of colluders affect the performance of collusion attack. In the literature, little effort has been made to explicitly study the relationship between risk, e.g., the probability of the colluders to be detected, and the distortion of the colluded signal. In this paper, we investigate the risk-distortion relationship for the linear video collusion attack with Gaussian fingerprint. We formulate the optimal linear collusion attack as an optimization problem of finding the optimal collusion parameters to minimize the distortion subject to a risk constraint. By varying the risk constraint and solving the corresponding optimization problem, we can derive the optimal risk-distortion curve. Moreover, based upon the observation that the detector/attacker can each improve the detection/attack performance with the knowledge of his/her opponent's strategy, we formulate the attack and detection problem as a dynamic mouse and cat game and study the optimal strategies for both the attacker and detector. We show that if the detector uses a fixed detection strategy, the attacker can estimate the detector's strategy and choose the corresponding optimal strategy to attack the fingerprinted video with a small distortion. However, if the detector is powerful, i.e., the detector can always estimate the attacker's strategy, the best strategy for the attacker is the min-max strategy. Finally, we conduct several experiments to verify the proposed risk-distortion model using real video data.

Human behavior analysis in video sharing social networks is an emerging research area, which analyzes the behavior of users who share multimedia content and investigates the impact of human dynamics on video sharing systems. Users watching live streaming in the same wireless network share the same limited bandwidth of backbone connection to the Internet, thus, they might want to cooperate with each other to obtain better video quality. These users form a wireless live-streaming social network. Every user wishes to watch video with high quality while paying as little as possible cost to help others. This paper focuses on providing incentives for user cooperation. We propose a game-theoretic framework to model user behavior and to analyze the optimal strategies for user cooperation simulation in wireless live streaming. We first analyze the Pareto optimality and the time-sensitive bargaining equilibrium of the two-person game. We then extend the solution to the multiuser scenario. We also consider potential selfish users' cheating behavior and malicious users' attacking behavior and analyze the performance of the proposed strategies with the existence of cheating users and malicious attackers. Both our analytical and simulation results show that the proposed strategies can effectively stimulate user cooperation, achieve cheat free and attack resistance, and help provide reliable services for wireless live streaming applications.

Collusion attack is a cost-effective attack against digital fingerprint. To develop an efficient collusion-resistant fingerprint scheme, it is very important for the detector to study the behavior of the colluders and the performance of collusion attack. Although several prior works have been proposed in the literature to analyze the performance of collusion attack, few effort has been made to explicitly study the relationship between risk, i.e., the probability of the colluders to be detected, and distortion of collusion attack. In this paper, we investigate the risk-distortion relationship of the linear video collusion attack with Gaussian fingerprint. We formulate the optimal linear collusion attack as an optimization problem, where the colluders try to minimize the distortion subject to a risk constraint. For any fixed risk constraint, the optimal distortion can be found using numerical optimization methods. By varying the risk constraint, we can obtain the risk-distortion model. We also conduct experiments to verify the proposed risk-distortion model using real video data.

Multimedia social network is a network infrastructure in which the social network members share multimedia contents with all different purposes. Analyzing user behavior in multimedia social networks help design more secured and efficient multimedia and networking systems. In this paper, we focus on the colluder social network in multimedia fingerprinting systems in which colluders gain reward by redistributing the colluded multimedia signal. However, the market value of the redistributed multimedia content is time sensitive. The earlier the colluded copy being released, the more the people who are willing to pay for it. Thus the colluders have to reach agreement on how to distribute reward and the probability being detected among themselves as soon as possible. This paper incorporates the time-sensitiveness of the colluders' reward, and models the dynamics among colluders as a noncooperative game, and studies the time-restricted bargaining equilibrium. We provide the solution to the equilibrium that all the colluders have no inventive to disagree in order to maximize their own payoff.

Multimedia social network analysis is an emerging research area, which analyzes the behavior of users who share multimedia content and investigates the impact of human dynamics on multimedia systems. Users watching live streaming in the same wireless network share the same backbone connection to the Internet, thus they might want to cooperate with each other to obtain better video quality. These users form a wireless live-streaming social network and every user wishes to watch video with as high as possible quality while paying as less as cost for cooperation. Thus full cooperation cannot be guaranteed and the cooperation strategy must give incentives to the users. This paper proposes a game-theoretic framework to model user behavior and designs incentive-based strategies to stimulate user cooperation in wireless live streaming. We analyze the Pareto optimality and time-restricted bargaining equilibrium of the game. We also take into consideration selfish users' cheating behavior and propose cheat-proof strategies. Both our analytical and simulation results show that the proposed strategies can effectively stimulate user cooperation, achieve cheat free and help provide reliable services.

Recent development in multimedia processing and network technologies has facilitated the distribution and sharing of multimedia through networks, and increased the security demands of multimedia contents. Traditional image content protection schemes use extrinsic approaches, such as watermarking or fingerprinting. However, under many circumstances, extrinsic content protection is not possible. Therefore, there is great interest in developing forensic tools via intrinsic fingerprints to solve these problems. Source coding is a common step of natural image acquisition, so in this paper, we focus on the fundamental research on digital image source coder forensics via intrinsic fingerprints. First, we investigate the unique intrinsic fingerprint of many popular image source encoders, including transform-based coding (both discrete cosine transform and discrete wavelet transform based), subband coding, differential image coding, and also block processing as the traces of evidence. Based on the intrinsic fingerprint of image source encoders, we construct an image source coding forensic detector that identifies which source encoder is applied, what the coding parameters are along with confidence measures of the result. Our simulation results show that the proposed system provides trustworthy performance: for most test cases, the probability of detecting the correct source encoder is over 90%.

In multimedia social networks, there exists complicated dynamics among users who share and exchange multimedia content. Using multimedia fingerprinting as an example, this paper investigates the human behavior dynamics in the multimedia social networks with side information. Side information is the information other than the colluded multimedia content that can help increase the probability of detection. We study the impact of side information in multimedia fingerprinting and show that the statistical means of the detection statistics can help the fingerprint detector significantly improve the collusion resistance. We then investigate how to probe the side information and model the dynamics between the fingerprint detector and the colluders as a two-stage extensive game with perfect information. We model the colluder-detector behavior dynamics as a two-stage game and find the equilibrium of the colluder-detector game using backward induction and show that the min-max solution is a Nash equilibrium, which gives no incentive for everyone in the multimedia fingerprint social network to deviate. This paper demonstrates that the proposed side information can significantly help improve the system performance to almost the same as the optimal correlation-based detector. Such result opens up a new scope in the research of fingerprinting system that given any fingerprint code, leveraging side information can improve the collusion resistance. Also, we provide the solutions to how to reach optimal collusion strategy and the corresponding detection, thus lead to a better protection of the multimedia content.

Multimedia social networks have become an emerging research area, in which analysis and modeling of the behavior of users who share multimedia are of ample importance in understanding the impact of human dynamics on multimedia systems. In peer-to-peer live-streaming social networks, users cooperate with each other to provide a distributed, highly scalable and robust platform for live streaming applications. However, every user wishes to use as much bandwidth as possible to receive a high-quality video, while full cooperation cannot be guaranteed. This paper proposes a game-theoretic framework to model user behavior and designs incentive-based strategies to stimulate user cooperation in peer-to-peer live streaming. We first analyze the Nash equilibrium and the Pareto optimality of two-person game and then extend to multiuser case. We also take into consideration selfish users' cheating behavior and malicious users' attacking behavior. Both our analytical and simulation results show that the proposed strategies can effectively stimulate user cooperation, achieve cheat free, attack resistance and help to provide reliable services.

Modulation forensics is to detect the modulation type in wireless communications without any prior information. It finds both military and civilian applications such as surveillance and cognitive radio. It is a challenging task, especially in a non-cooperative environment, as no prior information on the incoming signal is available at the receiver. In this paper, we investigate the modulation forensics of linear digital modulations and space-time orthogonal code in slowly varying frequency-selective fading channels. With unknown channel vector, and phase distortion at the receive-side, we derive a composite test consisting second-moment nonlinearity and maximum likelihood test, and discuss the performance and forensic system confidence measure. It is shown that the proposed algorithm achieves almost perfect identification of the space-time coding, and high accuracy rate of modulation type detection.

Multimedia social network analysis is an emerging research area, which analyzes the behavior of users who share multimedia content and investigates the impact of human dynamics on multimedia systems. In peer-to-peer live-streaming social networks, user cooperate with each other to provide a distributed, highly scalable and robust platform for live streaming applications. However, every user wishes to use as much bandwidth as possible to receive a high-quality video, and full cooperation cannot be guaranteed. This paper proposes a game-theoretic framework to model user behavior and designs incentive-based strategies to stimulate user cooperation in peer-to-peer live streaming. We analyze the Nash equilibrium and the Pareto optimality of the game. We also take into consideration selfish users' cheating behavior and propose cheat-proof strategies. Both our analytical and simulation results show that the proposed strategies can effectively stimulate user cooperation, achieve cheat free and help provide reliable services.

Multimedia social network analysis is a research area with growing importance, in which the social network members share multimedia contents with all different purposes and analyzing their behavior help design more secured and efficient multimedia and networking systems. In this paper, we focus on multimedia fingerprinting social network, in which multi-user collusion being a powerful attack, where a group of attackers collectively undermine the traitor tracing capability. During collusion, different colluders have different objective thus, the colluders form a social network and an how to achieve agreement on distributing the risk/profit among colluders and ensure fairness of the attack is a crucial question. This paper models the dynamics among colluders as a non-cooperative game, propose a general model of utility functions and study four different bargaining solutions of this game.

Multiuser collusion is an effective attack against traitor-tracing multimedia fingerprinting, where a group of attackers collectively mount attacks to reduce their risk of being detected. During collusion, each attacker wishes to maximize his or her own payoff. To resolve the conflict, colluders have to negotiate with each other and achieve fair collusion. An attacker also needs to decide with whom he or she wants to collude. Though colluding with more people helps further reduce the risk, it also makes an attacker share with more people the rewards from illegal usage of multimedia. This paper uses game theory to model the complex colluder dynamics and analyzes the tradeoff between the risk and the rewards. We study how the selection of fellow attackers affects each colluder's utility, and analyze the optimum strategies that maximize colluders' payoffs.

Digital fingerprinting is an emerging technology in media security to identify the source of illicit copies and trace traitors. Collusion is a powerful attack, in which a group of attacker collectively mount attacks against digital fingerprinting. In multimedia fingerprinting, there exists complex dynamics between the colluders and the fingerprint detector, who have conflicting objectives and influence each other's performance and decisions. This paper proposes a game-theoretic framework to formulate and analyze the colluder-detector dynamics, in an effort to understand its impact on the traitor tracing performance of multimedia fingerprints. We investigate how colluders adjusts the collusion attacks to minimize their risk under the fairness constraint; and study how the fingerprint detector adapts his/her detection strategy accordingly to improve the collusion resistance, which is shown to be the min-max solution.

In non-intrusive forensic analysis, we wish to find information and properties about a piece of data without any reference to the original data prior to processing. An important first step to forensic analysis is the detection and estimation of block processing. Most existing work in block measurement uses strong assumptions on the data related to the block size or the method of compression. In this paper, we propose a new method to estimate the block size in digital images in a blind manner for use in a forensic context. We make no assumptions on the block size or the nature of any previous processing. Our scheme can accurately estimate block sizes in images up to a PSNR of 42 dB where block artifacts are perceptually invisible. We also offer a measure of detection accuracy which correctly classifies an image as block-processed with a probability of 95.0% while keeping the probability of false alarm at 7.4%.

Multi-user collusion is an cost-effective attack against digital fingerprinting, in which a group of attackers collectively undermine the traitor tracing capability of digital fingerprints. However, during multi-user collusion, each colluder wishes to minimize his/her own risk and maximize his/her own profit, and different colluders have different objectives. Thus, an important issue during collusion is to agree on how to distribute the risk/profit among colluders and ensure fairness of the attack. To have a better understanding of the attackers' behavior during collusion to achieve fairness, this paper models the dynamics among colluders as a non-cooperative game. We then study the Pareto-optimal set, where no colluder can further increase his/her own payoff without decreasing others', and analyze the Nash bargaining solution of this game.

The area of non-intrusive forensic analysis has found many applications in the area of digital imaging. One unexplored area is the identification of source coding in digital images. In other words, given a digital image, can we identify which compression scheme was used, if any? This paper focuses on the aspect of transform coder classification, where we wish to determine which transform was used during compression. This scheme analyzes the histograms of coefficient subbands to determine the nature of the transform method. By obtaining the distance between the obtained histogram and the estimate of the original histogram, we can determine if the image was compressed using the transform tested. Results show that this method can successfully classify compression by transform as well as detect whether any compression has occurred at all in an image.

In this digital era, digital multimedia contents are often transmitted over networks without any protection. This raises serious security concerns since the receivers/subscribers do not know what processes have been applied to multimedia data, and neither do they know whether this copy comes from a trusted source. Therefore, it is critical to provide forensic tools to identify the history of operations applied to multimedia data. In this paper, we focus on the identification of source coding techniques applied to multimedia, and we investigate the forensic analysis of transform based coding (both DCT and DWT based), subband coding, and linear predictive coding. Using the intrinsic fingerprints as trace of evidences, we construct an image source coding forensic system that analyzes which source encoder is used to compress the image and provides confidence measurements. Our simulation results show that the proposed system provides trustworthy performance: the probability of detecting the correct source encoder is 0.82 when PSNR = 40 dB, and it can correctly identify the source encoder with probability 0.98 with PSNR = 20dB.

Digital fingerprinting uniquely labels each distributed copy with user's ID and provides a proactive means to track the distribution of multimedia. Multi-user collusion is a powerful attack against digital fingerprinting, in which a group of attackers collectively mount attacks to remove the embedded identification information. To resist such multi-user collusion and support multimedia forensics, this paper investigates the side information based multimedia fingerprinting. We explore techniques to utilize side information of collusion attacks during colluder identification process, and show that the means of the detection statistics at the detector's side can significantly improve the traitor tracing capability. We also investigate how the fingerprint detector can probe such side information from the colluded copy, and our simulation results show that the proposed scheme helps the fingerprint detector achieve the optimum detection performance.