The Internet of Drones (IoD) enables coordinated UAV communication for critical applications such as disaster response, military operations, and smart agriculture. As IoD networks scale and integrate with next-generation wireless systems (e.g., 6G), securing communication between resource-constrained drones becomes essential, particularly against replay attacks that can compromise safety and mission integrity. We present JKA-HT, a lightweight authentication and key agreement protocol offering robust, time-independent replay protection and comprehensive formal security guarantees. Building on the Julia Key Agreement (JKA), JKA-HT introduces HASHTAG, a novel cryptographic tagging mechanism that achieves replay resilience without relying on synchronized clocks or special hardware. We formally verify JKA-HT in the TAMARIN prover under the Dolev-Yao threat model, proving mutual authentication, forward/backward secrecy, Key Compromise Impersonation (KCI) resistance, and replay protection. JKA-HT is the first IoD authentication protocol to achieve all these properties with formal proofs, making it well-suited for deployment in adversarial, resource-constrained environments.

Rapid player motion, occlusions, substitutions, and jersey changes pose major challenges for identity-consistent tracking in sports. Existing multi-object tracking (MOT) methods struggle in long-term and multi-perspective settings like broadcast footage, where views change frequently. To address this, we first introduce MuPNIT, the first MOT and ReID benchmark to provide identity-consistent labeling under multi-perspective dynamics and long-term appearance variations across seasons, teams, and jersey changes. Second, we propose Global ID Fusion (GIF), a novel, online framework that performs single-pass global ID association and supports zero-shot identification. Our approach achieves state-of-the-art results, improving HOTA by 25.3% and IDF1 by 79.5% over OC-SORT. Finally, to assess identity consistency, we introduce five global ID metrics that reveal tradeoffs in tracking stability. By bridging MOT and ReID, our work advances identity-aware player tracking in sports and sets a new benchmark with applications in sports analytics, surveillance, and long-term person search. Code and datasets: https://github.com/Wojak27/GIF

In this study, we introduce MoMEP, a message transmission protocol relying on chameleon signatures. These signatures allow modification of signed messages while keeping the original signature valid. Despite their useful features, chameleon signatures have received limited use in real-world applications, such as internet protocols. Our work bridges this the gap by presenting a protocol based on chameleon signatures, and formally proving its trustworthiness using symbolic formal verification. In particular, providing accountability guarantees presents unique challenges, as message modifications can erase evidence of misbehavior, breaking traditional assumptions about trace-based accountability. To address this, we define three protocol-level accountability properties (i.e., unforgeability, non-repudiation, and non-frameability) for MoMEP, complementing earlier definitions applicable for cryptographic primitives. These properties are essential to allow symbolic protocol verification and ensure accountability for all relevant entities involved in the message exchange. We also introduce an entity accountability notion that does not rely on storing protocol traces and is based on an evidence-driven verdict function. We model MoMEP in the Tamarin theorem prover and formally verify that it satisfies our accountability properties. Finally, we prove the soundness and completeness of MoMEP’s evidence-based verdict function, reinforcing its correctness and applicability for deciding accountability in real-world scenarios.

Head movement data in virtual reality (VR), particularly during 360° video streaming, can reveal uniquely identifying behavioral patterns, posing serious privacy risks. While noise injection can obscure these signals, it often degrades the user’s Quality of Experience (QoE), creating a challenging privacy–utility tradeoff. We introduce Priv360, a client-side defense that injects carefully tuned noise into the transmitted 6-DoF head pose while preserving the user’s actual viewing experience. Before sending metadata to the server, the client reconstructs a stable predicted viewport from the noisy pose using a fast AR(2) model fused with a constant-jerk Kalman filter (with an optional LSTM-enhanced variant). Only this predicted viewport is transmitted for quality adaptation; the client continues to render the true viewport locally using the unperturbed pose. Using real 6-DoF datasets, including a newly collected Meta Quest~3 dataset, and a leave-one-video-out evaluation, we show that Priv360 substantially reduces re-identification accuracy while maintaining high visual quality across noise levels, prediction horizons, bandwidth settings, and attacker architectures. We further compare multiple prediction filters and show that combining learned and model-based predictors yields the most favorable privacy–QoE tradeoff. Our results provide a practical privacy defense and actionable insights for deploying privacy-aware VR streaming.

Fingerprinting attacks on encrypted network traffic may reveal sensitive information about users of anonymous communication systems, such as visited websites or watched videos, linking users' activities to their identities. Defenses come at the cost of bandwidth and delay overheads, impacting the user experience and making wide-scale deployment challenging. There is a rich history of attacks and defenses, with continual improvements in deep learning as a catalyst, making deployment of defenses an ever more pressing matter. This paper introduces a new defense strategy against fingerprinting attacks---ephemeral defenses---where efficient defense search enables the generation of unique per-connection defenses. We demonstrate that ephemeral defenses are multipurpose network-layer defenses against circuit, website, and video fingerprinting attacks, achieving competitive performance compared to related work. Furthermore, we create tunable ephemeral defenses that are not overly specialized to a particular fingerprinting attack, dataset, or network conditions. Ephemeral defenses are practical, demonstrated through integration with WireGuard and deployment at Mullvad VPN for a year, serving thousands of daily users.

As reliance on online video continues to increase throughout all facets of society, it is critical to address the security and privacy threat of video fingerprinting, in which a local, passive adversary monitors a victim’s encrypted connection to a video server to infer which videos they are watching. These attacks attain high accuracy in realistic scenarios, while defenses that offer an acceptable trade-off between protection, overhead, and user experience are lacking. In this paper, we motivate application-layer defenses against video fingerprinting and present Dodge, a client-side framework for application-layer video fingerprinting defenses, implemented as a fork of the dash.js video player. Dodge provides the infrastructure and building blocks for defenses as well as a plug-and-play interface, making defense development and use straightforward while still providing maximal control over video flows. As a proof of concept, we use Dodge to implement a mimicry defense and show through live deployments that Dodge and the defense operate seamlessly, with modest overhead and very low user experience impact, while reducing attacker success close to theoretical bounds. Dodge can easily be deployed at scale and in a number of scenarios, with no changes to servers or network components; our analyses also lead to a host of insights that we hope will aid in deployment efforts.

Cloud computing enables the dynamic provisioning of server resources. To exploit this opportunity, a policy is needed for dynamically allocating (and deallocating) servers in response to the current load conditions. In this paper we describe several simple policies for dynamic server allocation and develop analytic models for their analysis. We also design semi-Markov decision models that enable determination of the performance achieved with optimal policies, allowing us to quantify the performance gap between simple, easily implemented policies, and optimal policies. Finally, we apply our models to study the potential performance benefits of state-dependent routing in multi-site systems when using dynamic server allocation at each site. Insights from our results are valuable to service providers wanting to balance cloud service costs and delays.

Bitcoin and the Dark Web present an interesting synergy that enables both legitimate anonymity and illicit activities, making it an important landscape to understand, especially as the Dark Web, with its hidden services, relies heavily on Bitcoin as a pseudonymous currency for transactions. However, a lack of scalable tools and timely datasets has limited systematic analysis of this ecosystem. To address this gap, we introduce Venom, a scalable framework for mapping Bitcoin activity on the Dark Web. Venom integrates multithreaded crawling, data extraction, and dataset generation, resulting in a comprehensive resource that allows us to easily collect snapshots of over 177,000 onion sites in roughly 24 hours. With the paper, we share both the tool and an example snapshot containing both per-site metadata and Bitcoin transaction data. Preliminary analysis reveals concentrated activity among key players and widespread content mirroring, offering new insights into the Dark Web's economic structure. Venom provides a critical resource for advancing research and monitoring in this domain.

This paper analyzes how different rhetorical attributes in news tweets, specifically analytical, clout, perceptual, and risk language, influence user engagement across publishers with different bias and reliability ratings. Using the LIWC framework to quantify these linguistic dimensions in a 5.5 million tweets dataset covering 1,553 news publishers and capturing over 480 million tweet interactions, we perform and present a category-based analysis that captures the relative impact that such features have on the user engagement rates associated with different political bias and reliability categories. While highly biased and unreliable publishers saw increased engagement for clout and risk language, confirming audience biases, the least biased ones benefited more from analytical language. Perception language, on the other hand, uniformly reduced engagement. These insights not only further our understanding of persuasion tactics but also have implications for curbing misinformation by aligning recommendations with audience veracity and impartiality preferences.

Cryptocurrencies’ pseudonymity property poses regulatory challenges and has attracted illicit actors that try to avoid oversight. To counter this, the U.S. Treasury’s Office of Foreign Assets Control (OFAC) sanctions individuals and entities using Bitcoin for cybercrime, terrorism financing, and other illicit activities. However, the effectiveness of these measures remains uncertain. This study analyzes over 13 million Bitcoin transactions linked to sanctioned entities, tracing fund flows and exchange interactions. We find that ~175,000 BTC was moved before sanctions took effect, with only 50 BTC remaining post-sanction, indicating preemptive fund displacement. Cybercrime-linked addresses accounted for the largest transfers—sometimes exceeding $1 billion—while sanctioned entities favored large, direct transactions to exchanges. Despite activity dropping immediately after sanctions took effect, some entities continued transacting for up to 1,500 days, exposing enforcement gaps. Our findings highlight key challenges in sanction enforcement, including delayed restrictions, exchange compliance gaps, and strategic fund movements. These insights inform policymakers and regulators seeking to strengthen cryptocurrency financial controls.

The widespread use of facial recognition (FR) technology has heightened concerns about personal privacy. With surveillance systems becoming ubiquitous, the demand for effective privacy-enhancing technologies is growing urgent. In response to this challenge, we introduce DiffPrivate, a versatile technique designed to protect individuals from FR systems (FRS) through two distinct approaches: a Perturb-based and an Edit-based approach. The Perturb-based mode generates robust adversarial samples by manipulating the diffusion process of a latent diffusion model to alter identity-specific features, ensuring the preservation of visual fidelity to the original images. On the other hand, the Edit-based approach employs an additional DDPM model for fine-grain editing of attributes, allowing for more precise control over the appearance while subtly shifting the identity features to evade FRS. By leveraging the strengths of both modes, DiffPrivate effectively shields an individual's identity against advanced defense mechanisms like DiffPure, maintaining high image quality. Our experiments demonstrate that DiffPrivate achieves competitive attack performance in terms of success rates and transferability while producing more natural-looking adversarial images than state-of-the-art methods. Overall, DiffPrivate represents a significant step towards balancing personal privacy and image naturalness in the face of advancing FR technology.

The rapid expansion of cloud computing has transformed data storage and processing by providing unprecedented convenience and scalability. However, this progress is shadowed by significant data security challenges, primarily as users must rely on cloud service providers to enforce robust security protocols. Homomorphic encryption (HE) offers a potential solution by allowing computations on encrypted data, thereby maintaining confidentiality without compromising functionality. However, HE can be computationally intensive, raising concerns about its practicality in real-world applications, particularly when dealing with large files. Moreover, constantly re-encrypting an entire file after every modification is inefficient and introduces substantial performance overheads. While traditional delta encoding can be used to optimize bandwidth by transmitting only file modifications, it faces security and privacy concerns as the server must access unencrypted file contents. In this paper, we address these challenges by introducing a novel delta encoding scheme tailored for seamless compatibility with HE, enhancing data confidentiality while maintaining efficiency. Our approach minimizes the overhead of re-encryption and improves performance by encrypting and transmitting only the modified file parts. We evaluate the performance of our scheme across various parameters and test cases, comparing it to a state-of-the-art delta encoding approach. Our findings demonstrate many similarities while highlighting the tradeoffs of our HE-enabling solution. Additionally, we explore the performance impacts of integrating HE with our delta encoding scheme and provide insights into the practical constraints and requirements for real-world deployment in cloud computing environments.

Despite the clear dominance of video streaming traffic on the Internet and the significant ramifications of disclosure of which videos users are streaming, video fingerprinting has received relatively little attention compared to other traffic analysis domains. Existing attacks are tailored to undefended traffic and mostly rely on a few manually crafted features. Meanwhile, potential defenses are ad hoc, often impractical, and typically only mentioned briefly. Drawing from progress made on website fingerprinting, we aim to improve current standards for attacks and defenses for video streaming traffic while highlighting a critical and underexplored issue on today's Internet. We show that directional and timing-based attacks that leverage CNNs are competitive with state-of-the-art video fingerprinting attacks, in many cases with far less training data. We also provide the first extensive study of potential defenses, which considers performance against attacks, overheads, and user QoE; and we present a novel defense design that boasts both broader applicability and greater efficacy than existing proposals.

In this era of ubiquitous surveillance and online presence, protecting facial privacy has become a critical concern for individuals and society as a whole. Adversarial attacks have emerged as a promising solution to this problem, but current methods are limited in quality or are impractical for sensitive domains such as facial editing. This paper presents a novel adversarial image editing framework called StyleAdv, which leverages StyleGAN's latent spaces to generate powerful adversarial images, providing an effective tool against facial recognition systems. StyleAdv achieves high success rates by employing meaningful facial editing with StyleGAN while maintaining image quality, addressing a challenge faced by existing methods. To do so, the comprehensive framework integrates semantic editing, adversarial attacks, and face recognition systems, providing a cohesive and robust tool for privacy protection. We also introduce the ``residual attack`` strategy, using residual information to enhance attack success rates. Our evaluation offers insights into effective editing, discussing tradeoffs in latent spaces, optimal edits for our optimizer, and the impact of utilizing residual information. Our approach is transferable to state-of-the-art facial recognition systems, making it a versatile tool for privacy protection. In addition, we provide a user-friendly interface with multiple editing options to help users create effective adversarial images. Extensive experiments are used to provide insights and demonstrate that StyleAdv outperforms state-of-the-art methods in terms of both attack success rate and image quality. By providing a versatile tool for generating high-quality adversarial samples, StyleAdv can be used both to enhance individual users' privacy and to stimulate advances in adversarial attack and defense research.

The significant impact of Twitter in news dissemination underscores the need to understand what drives tweet popularity. While the content of an article plays a role, several "content-agnostic" factors also influence tweet popularity. Previous studies have faced challenges in differentiating the effects of content-agnostic factors from content variations. To address this, the paper presents a comprehensive analysis of tweet popularity using a "clone-based" approach. The methodology involves identifying tweets linking the same or similar articles (clones) and studying the factors that make some tweets within clone sets more successful in attracting retweets. The analysis reveals insights into clone set characteristics, winners' success patterns, retweet dynamics over time, domain-based competition, and predictors of success. The findings shed light on the complex nature of popularity and success in social media, providing a deeper understanding of the content-agnostic factors that influence tweet popularity.

Most state-of-the-art facial recognition systems (FRS:s) use face embeddings. In this paper, we present the IdDecoder framework, capable of effectively synthesizing realistic-neutralized face images from face embeddings, and two effective attacks on state-of-the-art facial recognition models using embeddings. The first attack is a black-box version of a model inversion attack that allows the attacker to reconstruct a realistic face image that is both visually and numerically (as determined by the FRS:s) recognized as the same identity as the original face used to create a given face embedding. This attack raises significant privacy concerns regarding the membership of the gallery dataset of these systems and highlights the importance of both the people designing and deploying FRS:s paying greater attention to the protection of the face embeddings than currently done. The second attack is a novel attack that performs the model inversion, so to instead create the face of an alternative identity that is visually different from the original identity but has close identity distance (ensuring that it is recognized as being of the same identity). This attack increases the attacked system's false acceptance rate and raises significant security concerns. Finally, we use IdDecoder to visualize, evaluate, and provide insights into differences between three state-of-the-art facial embedding models.

The underlying trading mechanisms of electronic securities exchanges have mostly stayed the same over the years with some additions and improvements. However, over the recent decade, high-frequency traders using algorithmic trading have shifted the field using practices that many consider unfair or unethical. In addition, insider trading continues to cause trust issues on certain trading platforms. In this paper, we present PET-Exchange, a privacy-preserving framework for trading securities on an electronic stock exchange. By using homomorphic encryption, PET-Exchange prevents information disclosures and unfair advantages in the trading processes. By matching and trading encrypted orders, we study the performance under various volumes and timing constraints, and compare this to the unencrypted counterparts. Our analysis of PET-Exchange using market trade data shows the privacy and cryptographic tradeoffs, demonstrating it to be suitable for small-scale trading and privacy-preserving auctions. Finally, we discuss the potential impact on transparency, fairness, and opportunities for financial crime in an electronic securities exchange. The insights we provide take us one step closer to a privacy-aware and fair public securities exchange.

In this work, we investigate the dynamic power management problem in a two-user secure broadcast channel scenario where the information at the source is kept in two separate queues, one for confidential and one for non-confidential information. The intended receiver of the confidential information transmits a jamming signal to prevent the other receiver from successfully decoding the confidential information. The decoding strategies used at the receivers include successive decoding (SD) and treating interference as noise (TIN). An autonomous agent, located at the source, decides on the power that will be used for the transmission of confidential information. We formulate the transmission power decision problem as a Markov Decision Process (MDP) and utilize the Deep Deterministic Policy Gradient (DDPG) algorithm for the agent to learn approximately optimal policies. We demonstrate that SD yields better rewards than TIN at the legitimate receiver. Additionally, we contrast the DDPG algorithm with three baseline power control policies and show that the former performs better than the latter.

Privacy of machine learning models is one of the remaining challenges that hinder the broad adoption of Artificial Intelligent (AI). This paper considers this problem in the context of image datasets containing faces. Anonymization of such datasets is becoming increasingly important due to their central role in the training of autonomous cars, for example, and the vast amount of data generated by surveillance systems. While most prior work de-identifies facial images by modifying identity features in pixel space, we instead project the image onto the latent space of a Generative Adversarial Network (GAN) model, find the features that provide the biggest identity disentanglement, and then manipulate these features in latent space, pixel space, or both. The main contribution of the paper is the design of a feature-preserving anonymization framework, StyleID, which protects the individuals’ identity, while preserving as many characteristics of the original faces in the image dataset as possible. As part of the contribution, we present a novel disentanglement metric, three complementing disentanglement methods, and new insights into identity disentanglement. StyleID provides tunable privacy, has low computational complexity, and is shown to outperform current state-of-the-art solutions.

Content-delivery applications can achieve scalability and reduce wide-area network traffic using geographically distributed caches. However, each deployed cache has an associated cost, and under time-varying request rates (e.g., a daily cycle) there may be long periods when the request rate from the local region is not high enough to justify this cost. Cloud computing offers a solution to problems of this kind, by supporting dynamic allocation and release of resources. In this article, we analyze the potential benefits from dynamically instantiating caches using resources from cloud service providers. We develop novel analytic caching models that accommodate time-varying request rates, transient behavior as a cache fills following instantiation, and selective cache insertion policies. Within the context of a simple cost model, we then develop bounds and compare policies with optimized parameter selections to obtain insights into key cost/performance tradeoffs. We find that dynamic cache instantiation can provide substantial cost reductions, that potential reductions strongly dependent on the object popularity skew, and that selective cache insertion can be even more beneficial in this context than with conventional edge caches. Finally, our contributions also include accurate and easy-to-compute approximations that are shown applicable to LRU caches under time-varying workloads.

The demand and usage of 360° video services are expected to increase. However, despite these services being highly bandwidth intensive, not much is known about the potential value that basic bandwidth saving techniques such as server or edge-network on-demand caching (e.g., in a CDN) could have when used for delivery of such services. This problem is both important and complicated as client-side solutions have been developed that split the full 360° view into multiple tiles, and adapt the quality of the downloaded tiles based on the user’s expected viewing direction and bandwidth conditions. This article presents new trace-based analysis methods that incorporate users’ viewports (the area of the full 360° view the user actually sees), a first characterization of the cross-user similarities of the users’ viewports, and a trace-based analysis of the potential bandwidth savings that caching-based techniques may offer under different conditions. Our analysis takes into account differences in the time granularity over which viewport overlaps can be beneficial for resource saving techniques, compares and contrasts differences between video categories, and accounts for uncertainties in the network conditions and the prediction of the future viewing direction when prefetching. The results provide substantial insight into the conditions under which overlap can be considerable and caching effective, and inform the design of new caching system policies tailored for 360° video.

Not all ad blockers achieve the same blocking success and, depending on their implementation, they can either improve or hurt the web performance experienced by users. Borgolte and Feamster (2020) recently provided the first extensive evaluation of how privacy-focused browser extensions affect a user's web performance. However, while their work provides a nice comparison of the performance impact that different extensions may have, their evaluation only considered landing pages of a single set of websites. In this paper, we focus specifically on performance comparisons when considering different sets of webpages. For example, we study the impact of whether a page is a landing page or an internal page, whether a page is popular or less popular, as well as the impact of in which country/region the company registering the website is operating (used as a proxy for the primary target market). For our evaluations, we use pairs of webpages carefully selected from the recently proposed Hispar list (Aqeel et al. 2020) and compare the performance of the most popular blocking extensions (Ad block Plus, uBlock Origin, Ghostery, and Private Badger) considered by Borgolte and Feamster with a baseline case in which we do not use any extension. While we observe clear differences in the distribution statistics of the metrics considered, several observations were consistent across all dimensions, including whether we consider landing pages or internal pages. The paper highlights some of these invariants and discusses their implications. In addition, our measurements (and the differences observed by different ad-blockers) also reveal new insights into how internal vs. landing pages of different web page categories (e.g., based on popularity or region) differ in their composition and resource usage.

Dual Connectivity (DC) is an important lower-layer feature accelerating the transition from 4G to 5G that also is expected to play an important role in standalone 5G radio networks. However, even though the packet reordering introduced by DC can significantly impact the performance of upper-layer protocols, no prior work has studied the impact of DC on QUIC. In this paper, we present the first such performance study. Using a series of throughput and fairness experiments, we show how QUIC is affected by different DC parameters, network conditions, and whether the DC implementation aims to improve throughput or reliability. Results for two QUIC implementations (aioquic, ngtcp2) and two congestion control algorithms (NewReno, CUBIC) are presented under both static and highly time-varying network conditions Our findings provide network operators with insights and understanding into the impacts of splitting QUIC traffic in a DC environment. With reasonably selected DC parameters and increased UDP receive buffers, QUIC over DC performs similarly to TCP over DC and achieves optimal fairness under symmetric link conditions when DC is not used for packet duplication. The insights can help network operators provide modern users with better end-to-end service when deploying DC.

With interactive branched video, the storyline is typically determined by branch choices made by the user during playback. Despite putting users in control of their viewing experiences, prior work has not considered how to best help users that may want to quickly navigate, explore, or skip parts of the branched video. Such functionalities are important for both impatient users and those rewatching the video. To address this void, we present the design, implementation and evaluation of interface solutions that help users effectively navigate the video, and to identify and explore previously unviewed storylines. Our solutions work with large, general video structures and allow users to effectively forward/rewind the branched structures. Our user study demonstrates the added value of our novel designs, presents promising tradeoffs, provides insights into the pros/cons of different design alternatives, and highlights the features that best address specific tasks and design aspects.

With 360° video streaming, the user's field of view (a.k.a. viewport) is at all times determined by the user's current viewing direction. Since any two users are unlikely to look in the exact same direction as each other throughout the viewing of a video, the frame-by-frame video sequence displayed during a playback session is typically unique. This complicates the direct comparison of the perceived Quality of Experience (QoE) using popular metrics such as the Multiscale-Structural Similarity (MS-SSIM). Furthermore, there is an absence of light-weight emulation frameworks for tiled-based 360° video streaming that allow easy testing of different algorithm designs and tile sizes. To address these challenges, we present REEFT-360, which consists of (1) a real-time emulation framework that captures tile-quality adaptation under time-varying bandwidth conditions and (2) a multi-step evaluation process that allows the calculation of MS-SSIM scores and other frame-based metrics, while accounting for the user's head movements. Importantly, the framework allows speedy implementation and testing of alternative head-movement prediction and tile-based prefetching solutions, allows testing under a wide range of network conditions, and can be used either with a human user or head-movement traces. The developed software tool is shared with the paper. We also present proof-of-concept evaluation results that highlight the importance of including a human subject in the evaluation.

The demand and usage of 360-degree video services are expected to increase. However, despite these services being highly bandwidth intensive, not much is known about the potential value that basic bandwidth saving techniques such as server or edge-network on-demand caching (e.g., in a CDN) could have when used for delivery of such services. This problem is both important and complicated as client-side solutions have been developed that split the full 360-degree view into multiple tiles, and adapt the quality of the downloaded tiles based on the user's expected viewing direction and bandwidth conditions. To better understand the potential bandwidth savings that caching-based techniques may offer for this context, this paper presents the first characterization of the similarities in the viewing directions of users watching the same 360-degree video, the overlap in viewports of these users (the area of the full 360-degree view they actually see), and the potential cache hit rates for different video categories and network conditions. The results provide substantial insight into the conditions under which overlap can be considerable and caching effective, and can inform the design of new caching system policies tailored for 360-degree video.

Since the advent of the Web, new Web benchmarking tools have frequently been introduced to keep up with evolving workloads and environments. The introduction of Web of Things (WoT) marks the beginning of another important paradigm that requires new benchmarking tools and testbeds. Such a WoT benchmarking testbed can enable the comparison of different WoT application configurations and workload scenarios under assumptions regarding WoT application resource demands and WoT device network characteristics. The powerful computational capabilities of modern commodity multicore servers along with the limited resource consumption footprints of WoT devices suggest the feasibility of a benchmarking testbed that can emulate the application behaviour of a large number of WoT devices on just a single multicore server. However, to obtain test results that reflect the true performance of the system being emulated, care must be exercised to detect and consider the impact of testbed bottlenecks on performance results. For example, if too many WoT devices are emulated then performance metrics obtained from a test run, e.g., WoT device response times, would only reflect contention among emulated devices for shared multicore server resources instead of providing a true indication of the performance of the WoT system being emulated. We develop a testbed that helps a user emulate a system consisting of multiple WoT devices on a single multicore server by exploiting Docker containers. Furthermore, we devise a novel mechanism for the user to check whether shared resource contention in the testbed has impacted the integrity of test results. Our solution allows for careful scaling of experiments and enables resource efficient evaluation of a wide range of WoT systems, architectures, application characteristics, workload scenarios, and network conditions.

News and information spread over social media can have big impact on thoughts, beliefs, and opinions. It is therefore important to understand the sharing dynamics on these forums. However, most studies trying to capture these dynamics rely only on Twitter's open APIs to measure how frequently articles are shared/retweeted, and therefore do not capture how many users actually read the articles linked in these tweets. To address this problem, in this paper, we first develop a novel measurement methodology, which combines the Twitter steaming API, the Bitly API, and careful sample rate selection to simultaneously collect and analyze the timeline of both the number of retweets and clicks generated by news article links. Second, we present a temporal analysis of the news cycle based on five-day-long traces (containing both clicks and retweet over time) for the news article links discovered during a seven-day period. Among other things, our analysis highlights differences in the relative timelines observed for clicks and retweets (e.g., retweet data often lags and underestimates the bias towards reading popular links/articles), and helps answer important questions regarding differences in how age-based biases and churn affect how frequently news articles shared on Twitter are accessed over time.

With client-side encryption (CSE), a user's data is encrypted before being transferred to a cloud provider. This ensures that only the intended user has access to the information, but complicates effective file synchronization (between different devices and the cloud). Motivated by prior findings that empirically show that the largest performance differences between popular CSE services (CSEs) and non-CSEs typically are related to the implementation of delta encoding solutions to reduce bandwidth usage, in this paper, we evaluate and provide insights into the practical CSE-related delta encoding overheads. First, we use targeted experiments to demonstrate the delta encoding problem associated with CSE and to compare the practical overhead differences associated with three example services implementing delta encoding. Second, we develop an analytic cost model and use it to show that a simple threshold-based CSE policy can reduce the bandwidth and storage usage seen by the best CSE considered here, that such a policy has a provable worst-case overhead within a factor two of the best non-CSE, and typically performs much better. The results are highly encouraging, and show that it is possible to provide CSE at limited additional overhead compared to non-CSE services.

During viewing of interactive "branched video", users are asked to make viewing choices that impact the storyline of the video playback. This type of video puts the users in control of their viewing experiences and provides content creators with great flexibility how to personalize the viewing experience of individual viewers. However, in contrast to with traditional video, where the use of a playback bar is default for most -- if not all -- players, there currently does not exist any generic playback bar for branched video that helps visualize the upcoming branch choices. Instead, most branched video implementations are typically custom-made on a per-video basis (e.g., see custom-made Netflix and BBC movies) and do not use a playback bar. As an important step towards addressing this void, we present the first branched video player with a generalized playback bar that visualizes the tree-like video structure and the buffer levels of the different branches. The player is implemented in dash.js and is made public with this publication, is the first of its kind, and allows both the playback bar and the presentation of branch choices to be customized with regards to visual appearance, functionality, and the content itself. Furthermore, the design is generic (making it applicable to any video) and allows content creators to easily create large numbers of branched movies using a simple metafile format. Finally, and most importantly, we perform a three-phase user study in which we evaluate the playback bar, compare with alternative designs, and other branch-related features. The user study highlights the value of a branched video playback bar, and provides interesting insights into how it and other design customization features may best be integrated into a player.

Due to widespread popularity of streaming services, many streaming clients typically compete over bottleneck links for their own bandwidth share. However, in such environments, the rate adaptation algorithms used by modern streaming clients often result in instability and unfairness, which negatively affects the playback experience. In addition, mobile clients often waste bandwidth by trying to stream excessively high video bitrates. We present and evaluate a cap-based framework in which the network and clients cooperate to improve the overall Quality of Experience (QoE). First, to motivate the framework, we conduct a comprehensive study using the lab setup showing that a fixed rate cap comes with both benefits (e.g., data savings, improved stability and fairness) and drawbacks (e.g., higher startup times and slower recovery after stalls). To address the drawbacks while keeping the benefits, we then introduce and evaluate a framework that includes (i) buffer-aware rate caps in which the network temporarily boosts the rate cap of clients during video startup and under low buffer conditions, and (ii) boost-aware client-side adaptation algorithms that optimize the bitrate selection during the boost periods. Combined with information sharing between the network and clients, these mechanisms are shown to improve QoE, while reducing wasted bandwidth.

With 360° video, only a limited fraction of the full view is displayed at each point in time. This has prompted the design of streaming delivery techniques that allow alternative playback qualities to be delivered for each candidate viewing direction. However, while prefetching based on the user's expected viewing direction is best done close to playback deadlines, large buffers are needed to protect against shortfalls in future available bandwidth. This results in conflicting goals and an important prefetch aggressiveness tradeoff problem regarding how far ahead in time from the current play-point prefetching should be done. This paper presents the first characterization of this tradeoff. The main contributions include an empirical characterization of head movement behavior based on data from viewing sessions of four different categories of 360° video, an optimization-based comparison of the prefetch aggressiveness tradeoffs seen for these video categories, and a data-driven discussion of further optimizations, which include a novel system design that allows both tradeoff objectives to be targeted simultaneously. By qualitatively and quantitatively analyzing the above tradeoffs, we provide insights into how to best design tomorrow's delivery systems for 360° videos, allowing content providers to reduce bandwidth costs and improve users' playback experiences.

The postal system is often used as an analogy when describing Internet routing. However, in addition to similarities, there are some significant differences. First, and most importantly, the Autonomous Systems (ASes) that operate the routers along the end-to-end path of a packet can often inspect and manipulate the packet and its content. Second, due to lack of secure routing mechanisms, packet paths can be diverted through additional non-trusted ASes. Although we often know the first network we connect through and the service that we access, we seldom know the networks that forward our packets. We can think of these networks as hidden mailmen. To better understand these networks and their potential access to information, we characterize the ASes along the paths of typical Internet packets between European example clients and the most popular web domains. We also identify ASes and countries with higher path coverage and investigate if there are differences in the HTTPS usage among paths that may take additional detours. Our results highlight the role played by North American (typically US-based) ASes and glean insights into how vulnerable the detoured traffic is to man-in-the-middle attacks compared to regular traffic.

Stalls during video playback are perhaps the most important indicator of a client's viewing experience. To provide the best possible service, a proactive network operator may therefore want to know the buffer conditions of streaming clients and use this information to help avoid stalls due to empty buffers. However, estimation of clients' buffer conditions is complicated by most streaming services being rate-adaptive, and many of them also encrypted. Rate adaptation reduces the correlation between network throughput and client buffer conditions. Usage of HTTPS prevents operators from observing information related to video chunk requests, such as indications of rate adaptation or other HTTP-level information.

Benchmarking is a widely-used technique to quantify the performance of software systems. However, the design and implementation of a benchmarking study can face several challenges. In particular, the time required to perform a benchmarking study can quickly spiral out of control, owing to the number of distinct variables to systematically examine. In this paper, we propose IRIS, an IteRative and Intelligent Experiment Selection methodology, to maximize the information gain while minimizing the duration of the benchmarking process. IRIS selects the region to place the next experiment point based on the variability of both dependent, i.e., response, and independent variables in that region. It aims to identify a performance function that minimizes the response variable prediction error for a constant and limited experimentation budget. We evaluate IRIS for a wide selection of experimental, simulated and synthetic systems with one, two and three independent variables. Considering a limited experimentation budget, the results show IRIS is able to reduce the performance function prediction error up to 4.3 times compared to equal distance experiment point selection. Moreover, we show that the error reduction can further improve through system-specific parameter tuning. Analysis of the error distributions obtained with IRIS reveals that the technique is particularly effective in regions where the response variable is sensitive to changes in the independent variables.

In contrast to traditional video, multi-view video streaming allows viewers to interactively switch among multiple perspectives provided by different cameras. One approach to achieve such a service is to encode the video from all of the cameras into a single stream, but this has the disadvantage that only a portion of the received video data will be used, namely that required for the selected view at each point in time. In this paper, we introduce the concept of a “multi-video stream bundle” that consists of multiple parallel video streams that are synchronized in time, each providing the video from a different camera capturing the same event or movie. For delivery we leverage the adaptive features and time-based chunking of HTTP-based adaptive streaming, but now employing adaptation in both content and rate. Users are able to change their viewpoint on-demand and the client player adapts the rate at which data are retrieved from each stream based on the user's current view, the probabilities of switching to other views, and the user's current bandwidth conditions. A crucial component of such a system is the prefetching policy. For this we present an optimization model as well as a simpler heuristic that can balance the playback quality and the probability of playback interruptions. After analytically and numerically characterizing the optimal solution, we present a prototype implementation and sample results. Our prefetching and buffer management solution is shown to provide close to seamless playback switching when there is sufficient bandwidth to prefetch the parallel streams.

The ephemeral content popularity seen with many content delivery applications can make indiscriminate on-demand caching in edge networks highly inefficient, since many of the content items that are added to the cache will not be requested again from that network. In this paper, we address the problem of designing and evaluating more selective edge-network caching policies. The need for such policies is demonstrated through an analysis of a dataset recording YouTube video requests from users on an edge network over a 20-month period. We then develop a novel workload modelling approach for such applications and apply it to study the performance of alternative edge caching policies, including indiscriminate caching and cache on kth request for different k. The latter policies are found able to greatly reduce the fraction of the requested items that are inserted into the cache, at the cost of only modest increases in cache miss rate. Finally, we quantify and explore the potential room for improvement from use of other possible predictors of further requests. We find that although room for substantial improvement exists when comparing performance to that of a perfect “oracle” policy, such improvements are unlikely to be achievable in practice.

This paper presents the design, implementation, and evaluation of an energy-efficient handover algorithm for the wireless sensor networks (WSNs) that are the main building block in the creation of the Internet of Things (IoT). Our low-power handover design is based on a careful breakdown and analysis of the potential power consumption of different components of the handover process. With the scanning part of the process being identified as the main drain of energy, the algorithm is designed to place the majority of the scanning responsibility on the mains powered access points, rather than on the low-power mobile nodes. The proposed algorithm has been implemented and its functionality and low power consumption have been empirically evaluated. We show that the design can reduce the energy consumption by several orders of magnitude compared to existing handover algorithms for WSNs. These reductions substantially extend the lifetime of low-power IoT devices with fixed battery capacity and reduce their battery requirements of other IoT devices.

Today, third-party tracking services and passive traffic monitoring are extensively used to gather knowledge about users' internet activities and interests. Such tracking has significant privacy implications for the end users. This paper presents an overview of the third-party tracking usage. Using measurements, we highlight the current state of the third-party tracking landscape and differences observed across tracking service classes (e.g., advertising, analytics, and content), across domain categories (e.g., popular vs. less popular, and national vs. global domains), and with regards to the organizations that owns many of the tracker services, when using HTTP and HTTPS, respectively. Understanding these differences help answer questions related to the third-party services that track modern web users and their coverage of our browsing.

When understanding modern web usage and providing optimized personalized service, it is important to identify the HTTP(S) requests directly caused by user actions like clicks and typing web addresses. With a majority of HTTP(S) requests being due to content that has not been explicitly requested by a user, the problem of identifying user actions at proxies or middleboxes becomes non-trivial. We present an automated evaluation framework for identifying user actions while also automatically providing a "ground truth" of the user actions. We utilize the framework to compare the performance of timing-based and HTTP-aware request classifiers, including timing-based classifiers operating on both per-request and per-connection basis to identify user actions. We emphasize the value of diverse information used by the classifiers when comparing identification accuracy both among classifiers and relative to the browser-based ground truth. Our classifiers can be useful to better understand users' web usage and connection prioritization.

The recent Energy Efficient Ethernet (EEE) standard and the eBond protocol provide two orthogonal approaches that allow significant energy savings on routers. In this paper we present the modeling and performance evaluation of these two protocols and a hybrid protocol. We first present eeeBond, pronounced ``triple-e bond'', which combines the eBond capability to switch between multiple redundant interfaces with EEE's active/idle toggling capability implemented in each interface. Second, we present an analytic model of the protocol performance, and derive closed-form expressions for the optimized parameter settings of both eBond and eeeBond. Third, we present a performance evaluation that characterizes the relative performance gains possible with the optimized protocols, as well as a trace-based evaluation that validates the insights from the analytic model. Our results show that there are significant advantages to combine eBond and EEE. The eBond capability provides good savings when interfaces only offer small energy savings when in short-term sleep states, and the EEE capability is important as short-term sleep savings improve.

Third-party identity management services enable cross-site information sharing, making Web access seamless but also raise significant privacy implications for the users. Using a combination of manual analysis of identified third-party identity management relationships and targeted case studies we capture how the protocol usage and third-party selection is changing, profile what information is requested to be shared (and actions to be performed) between websites, and identify privacy issues and practical problems that occur when using multiple accounts (associated with these services). The study highlights differences in the privacy leakage risks associated with different classes of websites, and shows that the use of multiple third-party websites, in many cases, can cause the user to lose (at least) partial control over which information is shared/posted on their behalf.

This paper considers the problem of providing users playing one streaming video the option of instantaneous and seamless playback of alternative videos. Recommendation systems can easily provide a list of alternative videos, but there is little research on how to best eliminate the startup time for these alternative videos. The problem is motivated by services that want to retain increasingly impatient users, who frequently watch the beginning of multiple videos, before viewing a video to the end. We present the design, implementation, and evaluation of an HTTP-based Adaptive Streaming (HAS) solution that provides careful prefetching and buffer management. We also present the design and evaluation of three fundamental policy classes that provide different tradeoffs between how aggressively new alternative videos are prefetched versus the importance of ensuring high playback quality. We show that our solution allows us to reduce the startup times of alternative videos by an order of magnitude and effectively adapt the quality such as to ensure the highest possible playback quality of the video being viewed. By improving the channel utilization we also address the discrimination problem that HAS clients often suffer from, allowing us to in some cases simultaneously improve the playback quality of the video being viewed and provide the value-added service of allowing instantaneous playback of the prefetched alternative videos.

To reduce energy consumption of lightly loaded routers, operators are increasingly incentivized to use Adaptive Link Rate (ALR) policies and techniques. These techniques typically save energy by adapting link service rates or by identifying opportune times to put interfaces into low-power sleep/idle modes. In this paper, we present a trace-based analysis of the impact that a router implementing these techniques has on the neighboring routers. We show that policies adapting the service rate at larger time scales, either by changing the service rate of the link interface itself or by changing which redundant heterogeneous link is active, typically have large positive effects on neighboring routers, with the downstream routers being able to achieve up-to 30% additional energy savings due to the upstream routers implementing ALR policies. Policies that save energy by temporarily placing the interface in a low-power sleep/idle mode, typically has smaller, but positive, impact on neighboring routers. Best are hybrid policies that use a combination of these two techniques. The hybrid policies consistently achieve the biggest energy savings, and have positive cascading effects on surrounding routers. Our results show that implementation of ALR policies can contribute to large-scale positive domino incentive effects, as they further increase the potential energy savings seen by those neighboring routers that consider implementing ALR techniques, while satisfying performance guarantees on the routers themselves.

Motivated by improved models for content workload prediction, in this paper we consider the problem of dynamic content allocation for a hybrid content delivery system that combines cloud-based storage with low cost dedicated servers that have limited storage and unmetered upload bandwidth. We formulate the problem of allocating contents to the dedicated storage as a finite horizon dynamic decision problem, and show that a discrete time decision problem is a good approximation for piecewise stationary workloads. We provide an exact solution to the discrete time decision problem in the form of a mixed integer linear programming problem, propose computationally feasible approximations, and give bounds on their approximation ratios. Finally, we evaluate the algorithms using synthetic and measured traces from a commercial music on-demand service and give insight into their performance as a function of the workload characteristics.

Interactive branched video that allows users to select their own paths through the video, provides creative content designers with great personalization opportunities; however, such video also introduces significant new challenges for the system developer. For example, without careful prefetching and buffer management, the use of multiple alternative playback paths can easily result in playback interruptions. In this paper, we present a full implementation of an interactive branched video player using HTTP-based Adaptive Streaming (HAS) that provides seamless playback even when the users defer their branch path choices to the last possible moment. Our design includes optimized prefetching policies that we derive under a simple optimization framework, effective buffer management of prefetched data, and the use of parallel TCP connections to achieve efficient buffer workahead. Through performance evaluation under a wide range of scenarios, we show that our optimized policies can effectively prefetch data of carefully selected qualities along multiple alternative paths such as to ensure seamless playback, offering users a pleasant viewing experience without playback interruptions.

SUMMARY The advent of multi‒core technology motivates new studies to understand how efficiently Web servers utilize such hardware. This paper presents a detailed performance study of a Web server application deployed on a modern eight‒core server. Our study shows that default Web server configurations result in poor scalability with increasing core counts. We study two different types of workloads, namely, a workload with intense TCP/IP related OS activity and the SPECweb2009 Support workload with more application‒level processing. We observe that the scaling behaviour is markedly different for these workloads, mainly because of the difference in the performance of static and dynamic requests. While static requests perform poorly when moving from using one socket to both sockets in the system, the converse is true for dynamic requests. We show that, contrary to what was suggested by previous work, Web server scalability improvement policies need to be adapted based on the type of workload experienced by the server. The results of our experiments reveal that with workload‒specific Web server configuration strategies, a multi‒core server can be utilized up to 80% while still serving requests without significant queuing delays; utilizations beyond 90% are also possible, while still serving requests with ‘acceptable’ response times. Copyright © 2014 John Wiley & Sons, Ltd.

This paper presents new results on characterization and modeling of user-generated video popularity evolution, based on a recent complementary data collection for videos that were previously the subject of an eight month data collection campaign during 2008/09. In particular, during 2011, we collected two contiguous months of weekly view counts for videos in two separate 2008/09 datasets, namely the ``recently-uploaded'' and the ``keyword-search'' datasets. These datasets contain statistics for videos that were uploaded within 7 days of the start of data collection in 2008 and videos that were discovered using a keyword search algorithm in 2008, respectively. Our analysis shows that the average weekly view count for the recently-uploaded videos had not decreased by the time of the second measurement period, in comparison to the middle and later portions of the first measurement period. The new data is used to evaluate the accuracy of a previously proposed model for synthetic view count generation for time periods that are substantially longer than previously considered. We find that the model yielded distributions of total (lifetime) video view counts that match the empirical distributions, however, significant differences between the model and empirical data were observed with respect to other metrics. These differences appear to arise because of particular popularity characteristics that change over time rather than being week-invariant as assumed in the model.

HTTP-based Adaptive Streaming (HAS) has become a widely-used video delivery technology. Use of HTTP enables relatively easy firewall/NAT traversal and content caching. While caching is an important aspect of HAS, there is not much public research on the performance impact proxies and their policies have on HAS. In this paper we build an experimental framework using open source Squid proxies and the most recent Open Source Media Framework (OSMF). A range of content-aware policies can be implemented in the proxies and tested, while the player software can be instrumented to measure performance as seen at the client. Using this framework, the paper makes three main contributions. First, we present a scenario-based performance evaluation of the latest version of the OSMF player. Second, we quantify the benefits using different proxy-assisted solutions, including basic best effort policies and more advanced content quality aware prefetching policies. Finally, we present and evaluate a cooperative framework in which clients and proxies share information to improve performance. In general, the bottleneck location and network conditions play central roles in which policy choices are most advantageous, as they significantly impact the relative performance differences between policy classes. We conclude that careful design and policy selection is important when trying to enhance HAS performance using proxy assistance.

The Zipf distribution is widely used to model Web site popularity, video popularity, and file referencing behavior. In recent published work, we proposed and evaluated a Zipf-based policy for probabilistic piece selection in Peer-to-Peer (P2P) media streaming. In this current paper, we revisit this Zipf model in more detail, and identify two fundamentally different modeling approaches, namely regenerative versus degenerative Zipf models. We illustrate the differences between the two models, provide refined analytical models for each, and validate the models with simulations in the context of P2P media streaming. The results show that the regenerative model is more appropriate for P2P streaming, because of its stronger sequential progress.

A long list of personal tragedies, including teenage suicides, has raised the importance of managing the personal information available on the Internet. It has been argued that it should be allowed to make mistakes, and that there should be a right to be forgotten. Unfortunately, today's Internet architecture and services typically do not support such functionality. We design a system that provides digital oblivion for users of online social networks. Participants form a peer-based agent community, which agree on protecting the privacy of individuals who request images to be forgotten. The system distributes and maintains up-to-date information on oblivion requests, and implements a filtering functionality when accessing an underlying online social network. We describe digital oblivion in terms of authentication of user-to-content relations and identify two user-to-content relations that are particularly relevant for digital oblivion. Finally, we design a family of protocols that provide digital oblivion with respect to these user-to-content relations, within the community that are implementing the protocol. Our protocols leverage a combination of digital signatures, watermarking, image tags, and trust management. No collaboration is required from the social network provider, although the system could also be incorporated as a standard feature of the social network.

Improving the performance and scalability of Web servers enhances user experiences and reduces the costs of providing Web-based services. The advent of Multi-core technology motivates new studies to understand how efficiently Web servers utilize such hardware. This paper presents a detailed performance study of a Web server application deployed on a modern 2 socket, 4-cores per socket server. Our study show that default, "out-of-the-box" Web server configurations can cause the system to scale poorly with increasing core counts. We study two different types of workloads, namely a workload that imposes intense TCP/IP related OS activity and the SPECweb2009 Support workload, which incurs more application-level processing. We observe that the scaling behaviour is markedly different for these two types of workloads, mainly due to the difference in the performance characteristics of static and dynamic requests. The results of our experiments reveal that with workload-specific Web server configuration strategies a modern Multi-core server can be utilized up to 80% while still serving requests without significant queuing delays; utilizations beyond 90% are also possible, while still serving requests with acceptable response times.

With BitTorrent, efficient peer upload utilization is achieved by splitting contents into many small pieces, each of which may be downloaded from different peers within the same swarm. Unfortunately, piece and bandwidth availability may cause the file-sharing efficiency to degrade in small swarms with few participating peers. Using extensive measurements, we identified hundreds of thousands of torrents with several small swarms for which reallocating peers among swarms and/or modifying the peer behavior could significantly improve the system performance. Motivated by this observation, we propose a centralized and a distributed protocol for dynamic swarm management. The centralized protocol (CSM) manages the swarms of peers at minimal tracker overhead. The distributed protocol (DSM) manages the swarms of peers while ensuring load fairness among the trackers. Both protocols achieve their performance improvements by identifying and merging small swarms and allow load sharing for large torrents. Our evaluations are based on measurement data collected during eight days from over 700 trackers worldwide, which collectively maintain state information about 2.8 million unique torrents. We find that CSM and DSM can achieve most of the performance gains of dynamic swarm management. These gains are estimated to be up to 40% on average for small torrents.

The World Wide Web and the services it provides are continually evolving. Even for a single time instant, it is a complex task to methodologically determine the infrastructure over which these services are provided and the corresponding effect on user perceived performance. For such tasks, researchers typically rely on active measurements or large numbers of volunteer users. In this paper, we consider an alternative approach, which we refer to as passive crowd-based monitoring. More specifically, we use passively collected proxy logs from a global enterprise to observe differences in the quality of service (QoS) experienced by users on different continents. We also show how this technique can measure properties of the underlying infrastructures of different Web content providers. While some of these properties have been observed using active measurements, we are the first to show that many of these properties (such as location of servers) can be obtained using passive measurements of actual user activity. Passive crowd-based monitoring has the advantages that it does not add any overhead on Web infrastructure, it does not require any specific software on the clients, but still captures the performance and infrastructure observed by actual Web usage.

Video dissemination through sites such as YouTube can have widespread impacts on opinions, thoughts, and cultures. Not all videos will reach the same popularity and have the same impact. Popularity differences arise not only because of differences in video content, but also because of other "content-agnostic" factors. The latter factors are of considerable interest but it has been difficult to accurately study them. For example, videos uploaded by users with large social networks may tend to be more popular because they tend to have more interesting content, not because social network size has a substantial direct impact on popularity. In this paper, we develop and apply a methodology that is able to accurately assess, both qualitatively and quantitatively, the impacts of various content-agnostic factors on video popularity. When controlling for video content, we observe a strong linear "rich-get-richer" behavior, with the total number of previous views as the most important factor except for very young videos. The second most important factor is found to be video age. We analyze a number of phenomena that may contribute to rich-get-richer, including the first-mover advantage, and search bias towards popular videos. For young videos we find that factors other than the total number of previous views, such as uploader characteristics and number of keywords, become relatively more important. Our findings also confirm that inaccurate conclusions can be reached when not controlling for content.

Cyberlockers have recently become a very popular means of distributing content. Today, cyberlocker traffic accounts for a non-negligible fraction of the total Internet traffic volume, and is forecasted to grow significantly in the future. The underlying protocol used in cyberlockers is HTTP, and increased usage of these services could drastically alter the characteristics of Web traffic. In light of the evolving nature of Web traffic, updated traffic models are required to capture this change. Despite their popularity, there has been limited work on understanding the characteristics of traffic flows originating from cyberlockers. Using a year-long trace collected from a large campus network, we present a comprehensive characterization study of cyberlocker traffic at the transport layer. We use a combination of flow-level and host-level characteristics to provide insights into the behavior of cyberlockers and their impact on networks. We also develop statistical models that capture the salient features of cyberlocker traffic. Studying the transport-layer interaction is important for analyzing reliability, congestion, flow control, and impact on other layers as well as Internet hosts. Our results can be used in developing improved traffic simulation models that can aid in capacity planning and network traffic management.

One highly-scalable approach to content delivery is to harness the upload bandwidth of the clients. Peer-assisted content delivery systems have been shown to effectively offload the servers of popular files, as the request rates of popular content enable the formation of self-sustaining torrents, where the entire content of the file is available among the peers themselves. However, for less popular files, these systems are less helpful in offloading servers. With a long tail of mildly popular content, with a high aggregate demand, a large fraction of the file requests must still be handled by servers. In this paper, we present the design, implementation, and evaluation of a dynamic file bundling system, where peers are requested to download content which they may not otherwise download in order to “inflate” the popularity of less popular files. Our system introduces the idea of a super bundle, which consists of a large catalogue of files. From this catalogue, smaller bundles, consisting of a small set of files, can dynamically be assigned to individual users. The system can dynamically adjust the number of downloaders of each file and thus enables the popularity inflation to be optimized according to current file popularities and the desired tradeoff between download times and server resource usage. The system is evaluated on PlanetLab.

We present a comprehensive longitudinal characterization study of the dynamics of content sharing in the global file hosting landscape. We leverage datasets collected from multiple vantage points that allow us to understand how usage of these services evolve over time and how traffic is directed into and out of these sites. We analyze the characteristics of hosted content in the public domain, and investigate the dissemination mechanisms of links. To the best of our knowledge, this is the largest detailed characterization study of the file hosting landscape from a global viewpoint.

With the proliferation of cloud services, cloud-based systems can become a cost-effective means of on-demand content delivery. In order to make best use of the available cloud bandwidth and storage resources, content distributors need to have a good understanding of the tradeoffs between various system design choices. In this work we consider a peer-assisted content delivery system that aims to provide guaranteed average download rate to its customers. We show that bandwidth demand peaks for contents with moderate popularity, and identify these contents as candidates for cloud-based service. We then consider dynamic content bundling (inflation) and cross-swarm seeding, which were recently proposed to improve download performance, and evaluate their impact on the optimal choice of cloud service use. We find that much of the benefits from peer seeding can be achieved with careful torrent inflation, and that hybrid policies that combine bundling and peer seeding often reduce the delivery costs by 20% relative to only using seeding. Furthermore, all these peer-assisted policies reduce the number of files that would need to be pushed to the cloud. Finally, we show that careful system design is needed if locality is an important criterion when choosing cloud-based service provisioning.

This paper develops analytical models that characterize the behavior of on-demand stored media content delivery using BitTorrent-like protocols. The models capture the effects of different piece selection policies, including Rarest-First, two variants of In-Order, and two probabilistic policies (Portion and Zipf). Our models provide insight into system behavior and help explain the sluggishness of the system with In-Order streaming. We use the models to compare different retrieval policies across a wide range of system parameters, including peer arrival rate, upload/download bandwidth, and seed residence time. We also provide quantitative results on the startup delays and retrieval times for streaming media delivery. Our results provide insights into the design tradeoffs for on-demand media streaming in peer-to-peer networks. Finally, the models are validated using simulations.

Peer-assisted content delivery systems can provide scalable download service for popular files. For mildly popular content, however, these systems are less helpful in offloading servers as the request rate for less popular files may not enable formation of self-sustaining torrents (where the entire content of the file is available among the peers themselves). As there typically is a long tail of mildly popular content, with a high aggregate demand, a large fraction of the file requests must still be handled by servers, and is not off-loadable to peers. Bundling approaches have been proposed where peers are requested to download content which they may not otherwise be interested in order to ``inflate'' the popularity of less popular files. We present the design and implementation of a dynamic bundling system, in which a large number of files may be bundled to form a super bundle. From this super bundle, smaller individual bundles, consisting of a small set of files, can dynamically be assigned to individual users. Our system has the capability to dynamically adjust the number of downloaders of each file, thus allowing popularity inflation to be optimized according to current file popularities.

Tracker-based peer-discovery is used in most commercial peer-to-peer content distribution systems, as it provides performance benefits compared to distributed solutions, and facilitates the control and monitoring of the overlay. But a tracker is a central point of failure, and its deployment and maintenance incur costs; hence an important question is how high tracker availability can be achieved at low cost. We investigate highly available, low overhead peer discovery, using independent trackers and a simple gossip protocol. This work is a step towards understanding the trade-off between the overhead and the achievable peer connectivity in highly available distributed overlay-management systems for peer-to-peer content distribution. We propose two protocols that connect peers in different swarms efficiently with a constant, but tunable, overhead. The two protocols, Random Peer Migration (RPM) and Random Multi-Tracking (RMT), employ a small fraction of peers in a torrent to virtually increase the size of swarms. We develop analytical models of the protocols based on renewal theory, and validate the models using both extensive simulations and controlled experiments. We illustrate the potential value of the protocols using large-scale measurement data that contains hundreds of thousands of public torrents with several small swarms, with limited peer connectivity. We estimate the achievable gains to be up to 40% on average for small torrents.

Globally, vast infrastructures of Information Technology (IT) equipment are deployed. Much of this infrastructure is under utilized to ensure acceptable response times. This results in less than ideal use of the capital investment used to purchase the IT equipment. To improve the sustainability of IT, we focus on increasing the effective utilization of computer systems. Our results show that computer systems running delay-sensitive (e.g., Web) workloads can be more effectively utilized while still maintaining adequate (e.g., mean or upper percentile) response times. In particular, these computer systems can simultaneously support delay-tolerant workloads, to increase the value of work done by a computer system over time.

There is a continuous struggle for control of resources at every organization that is connected to the Internet. The local organization wishes to use its resources to achieve strategic goals. Some external entities seek direct control of these resources, for purposes such as spamming or launching denial-of-service attacks. Other external entities seek indirect control of assets (e.g., users, finances), but provide services in exchange for them. Using a year-long trace from an edge network, we examine what various external organizations know about one organization. We compare the types of information exposed by or to external organizations using either active ( reconnaissance ) or passive ( surveillance ) techniques. We also explore the direct and indirect control external entities have on local IT resources.

Today’s Web provides many different functionalities, including communication, entertainment, social networking, and information retrieval. In this article, we analyze traces of HTTP activity from a large enterprise and from a large university to identify and characterize Web-based service usage. Our work provides an initial methodology for the analysis of Web-based services. While it is nontrivial to identify the classes, instances, and providers for each transaction, our results show that most of the traffic comes from a small subset of providers, which can be classified manually. Furthermore, we assess both qualitatively and quantitatively how the Web has evolved over the past decade, and discuss the implications of these changes.

Video sharing services that allow ordinary Web users to upload video clips of their choice and watch video clips uploaded by others have recently become very popular. This article identifies invariants in video sharing workloads, through comparison of the workload characteristics of four popular video sharing services. Our traces contain metadata on approximately 1.8 million videos which together have been viewed approximately 6 billion times. Using these traces, we study the similarities and differences in use of several Web 2.0 features such as ratings, comments, favorites, and propensity of uploading content. In general, we find that active contribution, such as video uploading and rating of videos, is much less prevalent than passive use. While uploaders in general are skewed with respect to the number of videos they upload, the fraction of multi-time uploaders is found to differ by a factor of two between two of the sites. The distributions of lifetime measures of video popularity are found to have heavy-tailed forms that are similar across the four sites. Finally, we consider implications for system design of the identified invariants. To gain further insight into caching in video sharing systems, and the relevance to caching of lifetime popularity measures, we gathered an additional dataset tracking views to a set of approximately 1.3 million videos from one of the services, over a twelve-week period. We find that lifetime popularity measures have some relevance for large cache (hot set) sizes (i.e., a hot set defined according to one of these measures is indeed relatively “hot”), but that this relevance substantially decreases as cache size decreases, owing to churn in video popularity.

As more and more organizations rely on the Internet for their daily operation, Internet security becomes increasingly critical. Unfortunately, the vast resources available on the Internet are attracting many malicious users and organizations, including organized crime syndicates. With such organizations disguising their activity by operating from the machines owned and operated by legitimate organizations, we argue that responsible organizations could improve overall Internet security by strengthening their own. By improving their organizational etiquette, legitimate organizations will make it more difficult for malicious users and organizations to hide. Towards this goal, we propose a system to identify and eliminate malicious activity on edge networks. We use a year-long trace of activity from an edge network to characterize the malicious activity at an edge network and demonstrate the potential effectiveness of our system.

BitTorrent-like swarming technologies are very effective for popular content, but less so for the `long tail' of files with disparate popularities, which do not have sufficiently many peers to enable efficient collaboration. Performance degradations are especially pronounced in swarms with reduced file availability. Static bundling groups files into a single data content. It requires no modification to the BitTorrent client, and has been shown to improve availability of unpopular files in BitTorrent swarms. However, as peers are forced to download undesired file pieces, download times increase, especially for peers downloading popular files. We propose to use Stochastic Games and Markov Decision Process (MDP) to model and analyze optimal peer strategies, in a selfish and a cooperative setting respectively, for a BitTorrent-like system with multiple files. Each peer wishes to download a subset of the files, and we allow peers to dynamically decide whether to collaborate with peers targeting a different set of files or not, given the current system state. The Stochastic Game and MPD models take into account both piece availability and average download times, and allow us to study if and when downloading unwanted content can be beneficial. We use dynamic programming to solve the two models, contrast the level of collaboration observed in the selfish and the cooperative settings, and propose an enhanced piece selection mechanism for BitTorrent-like systems with dynamic download decision making. We demonstrate the effectiveness of dynamic file piece selection through both simulations and experiments using a modified BitTorrent client.

With a majority of Internet traffic being predicted to be caused by content delivery, it is clear that content delivery applications will consume much of the resources on the Internet. This paper considers the problem of cost-efficient content delivery, in which the application incurs both a network delivery cost (e.g., from cross ISP traffic or, more generally, operation/energy costs at Internet routers) and costs at the servers (e.g., due to cost of ownership, energy, or disk bandwidth). While the cost objective and the absolute cost tradeoff may be different from case to case, we argue that an architecture with distributed servers, each using digital fountain delivery, may be an attractive candidate architecture when considering the total content delivery cost. Within the context of a simple system model, we then determine optimal server selection policies for such an architecture, and derive analytic expressions for their associated delivery costs. A readily-implementable heuristic policy is proposed that is found to achieve within 10% of the minimal cost. Finally, we show how our results for content download can also be applied to streaming video delivery.

Video on demand, particularly with user-generated content, is emerging as one of the most bandwidth-intensive applications on the Internet. Owing to content control and other issues, some video-on-demand systems attempt to prevent downloading and peer-to-peer content delivery. Instead, such systems rely on server replication, such as via third-party content distribution networks, to support video streaming (or pseudostreaming) to their clients. A major issue with such systems is the cost of the required server resources. By synchronizing the video streams for clients that make closely spaced requests for the same video from the same server, server costs (such as for retrieval of the video data from disk) can be amortized over multiple requests. A fundamental trade-off then arises, however, with respect to server selection. Network delivery cost is minimized by selecting the nearest server, while server cost is minimized by directing closely spaced requests for the same video to a common server. This article compares classes of server selection policies within the context of a simple system model. We conclude that: (i) server selection using dynamic system state information (rather than only proximities and average loads) can yield large improvements in performance, (ii) deferring server selection for a request as late as possible (i.e., until just before streaming is to begin) can yield additional large improvements, and (iii) within the class of policies using dynamic state information and deferred selection, policies using only “local” (rather than global) request information are able to achieve most of the potential performance gains.

Many factors such as the tendency of individuals to develop relationships based on mutual acquaintances, proximity, common interests, or combinations thereof, are known to contribute toward evolution of social networks. In this paper, we analyze an evolving online social aggregator FriendFeed, which collates content generated by participating individuals on a variety of Web 2.0 services and allows easy dissemination of the aggregated content to other participants of the aggregator. Analyzing data collected between September 2008 and May 2009, we find that although preferential attachment captures the evolution of the network, its influence varies significantly based on how long ago a user joined the service. In particular, preferential attachment does not appear to apply to new entrants of the FriendFeed service. Analysis suggests that proximity bias plays an important role in link formation. We study the influence of common foci and find that individuals have a greater affinity toward those with similar interests.

Maintaining low power consumption is critical in wireless ad hoc and sensor networks. With packet transmissions and retransmissions consuming much of the energy resources in wireless networks, it becomes important to minimize the number of transmissions associated with the end-to-end delivery of packets. Power-aware routing algorithms must balance the advantages and disadvantages of selecting to forward packets over shorter high-quality links against selecting longer and less reliable links. This paper proposes a new power-aware geographic routing technique that combines geographic greedy routing with probabilistic random walks to recover from local minima (i.e., cases when the forwarding node is not aware of any neighboring node providing "greedy" progress towards the destination). Building upon previous power-aware protocols without recovery mechanisms, our protocol uses simple distance metrics that combine information about the individual reception rates between node pairs and the relative forward progress candidate nodes provide towards the target destination. The combined metrics are used to make greedy choices (when at least one node provides progress) and probabilistic choices (when the packet recovers from a local minimum). Using simulations we show that power-aware routing significantly reduces the energy consumption in the network, and our probabilistic recovery mechanism can significantly increase the delivery rates with only a small decrease in energy efficiency.

No abstract available.

This paper develops analytic models that characterize the behavior of on-demand stored media content delivery using BitTorrent-like protocols. The models capture the effects of different piece selection policies, including Rarest-First and two variants of In-Order. Our models provide insight into transient and steady-state system behavior, and help explain the sluggishness of the system with strict In-Order streaming. We use the models to compare different retrieval policies across a wide range of system parameters, including peer arrival rate, upload/download bandwidth, and seed residence time. We also provide quantitative results on the startup delays and retrieval times for streaming media delivery. Our results provide insights into the optimal design of peer-to-peer networks for on-demand media streaming.

Conventional video consists of a single sequence of video frames. During a client's playback period, frames are viewed sequentially from some specified starting point. The fixed frame ordering of conventional video enables efficient scheduled broadcast delivery, as well as efficient near on-demand delivery to large numbers of concurrent clients through use of periodic broadcast protocols in which the video file is segmented and transmitted on multiple channels. This paper considers the problem of devising scalable protocols for near on-demand delivery of "nonlinear" media files whose content may have a tree or graph, rather than linear, structure. Such media allows personalization of the media playback according to individual client preferences. We formulate a mathematical model for determination of the optimal periodic broadcast protocol for nonlinear media with piecewise-linear structures. Our objective function allows differing weights to be placed on the startup delays required for differing paths through the media. Studying a number of simple nonlinear structures we provide insight into the characteristics of the optimal solution. For cases in which the cost of solving the optimization model is prohibitive, we propose and evaluate an efficient approximation algorithm.

Previous scalable protocols for downloading large, popular files from a single server include batching and cyclic multicast. With batching, clients wait to begin receiving a requested file until the beginning of its next multicast transmission, which collectively serves all of the waiting clients that have accumulated up to that point. With cyclic multicast, the file data is cyclically transmitted on a multicast channel. Clients can begin listening to the channel at an arbitrary point in time, and continue listening until all of the file data has been received. This paper first develops lower bounds on the average and maximum client delay for completely downloading a file, as functions of the average server bandwidth used to serve requests for that file, for systems with homogeneous clients. The results show that neither cyclic multicast nor batching consistently yields performance close to optimal. New hybrid download protocols are proposed that achieve within 15 % of the optimal maximum delay and 20 % of the optimal average delay in homogeneous systems. For heterogeneous systems in which clients have widely-varying achievable reception rates, an additional design question concerns the use of high rate transmissions, which can decrease delay for clients that can receive at such rates, in addition to low rate transmissions that can be received by all clients. A new scalable download protocol for such systems is proposed, and its performance is compared to that of alternative protocols as well as to new lower bounds on maximum client delay. The new protocol achieves within 25 % of the optimal maximum client delay in all scenarios considered.