Increasingly, web content is automatically generated by large language models (LLMs) with little human input. We call this ''LLM-dominant'' content. Since LLMs plagiarize and hallucinate, LLM-dominant content can be unreliable and unethical. Yet, websites rarely disclose such content, and human readers struggle to distinguish it. Thus, we must develop reliable detectors for LLM-dominant content. However, state-of-the-art LLM detectors are inaccurate on web content, because web content has low positive rates, complex markup, and diverse genres, instead of clean, prose-like benchmark data SoTA detectors are optimized for.

Operators of web archives have two options for how to crawl pages from the web. Browser-based dynamic crawlers capture all of the resources on every page, but incur high compute overheads. Static browserless crawlers are more lightweight, but miss page resources which are fetched only when scripts are executed.

Today, large-scale software-defined networks use microservice-based controllers. Bugs in these controllers can reduce network availability by making the data plane state inconsistent with the high-level intent. To recover from such inconsistencies, modern controllers periodically reconcile the state of all the switches with the desired intent. However, periodic reconciliation limits the availability and performance of the network at scale. We introduce Zenith, a microservice-based controller that avoids inconsistencies by design rather than always relying on recovery mechanisms. We have formally verified Zenith's specifications and have proved that it ensures the network state will eventually be consistent with intent. We automatically generate Zenith's code from its specification to minimize the likelihood of errors in the final implementation. Zenith's guarantees and abstractions also enable developers to independently verify SDN applications and ensure end-to-end safety and correctness. Zenith resolves inconsistencies 5× faster than today's designs and significantly improves availability.

Federated learning (FL) is an emerging machine learning (ML) paradigm that enables heterogeneous edge devices to collaboratively train ML models without revealing their raw data to a logically centralized server. However, beyond the heterogeneous device capacity, FL participants often exhibit differences in their data distributions, which are not independent and identically distributed (Non-IID). Many existing works present point solutions to address issues like slow convergence, low final accuracy, and bias in FL, all stemming from client heterogeneity.

The web is littered with millions of links which previously worked but no longer do. When users encounter any such broken link, they resort to looking up an archived copy of the linked page. But, for a sizeable fraction of these broken links, no archived copies exist. Even if a copy exists, it often poorly approximates the original page, e.g., any functionality on the page which requires the client browser to communicate with the page's backend servers will not work, and even the latest copy will be missing updates made to the page's content after that copy was captured.

It is common for the authors of a web page to include links to related pages on other sites. However, when users visit a page several years after it was last updated, they often find that some of the external links either do not work or point to unrelated content. To combat these problems of link rot and content drift, the solution used today is to capture a copy of the linked page when a link is created and serve this copy to users who choose to visit the link.

We present FedScale, a federated learning (FL) benchmarking suite with realistic datasets and a scalable runtime to enable reproducible FL research. FedScale datasets encompass a wide range of critical FL tasks, ranging from image classification and object detection to language modeling and speech recognition. Each dataset comes with a unified evaluation protocol using real-world data splits and evaluation metrics. To reproduce realistic FL behavior, FedScale contains a scalable and extensible runtime. It provides high-level APIs to implement FL algorithms, deploy them at scale across diverse hardware and software backends, and evaluate them at scale, all with minimal developer efforts. We combine the two to perform systematic benchmarking experiments and highlight potential opportunities for heterogeneity-aware co-optimizations in FL. FedScale is open-source and actively maintained by contributors from different institutions at http://fedscale.ai. We welcome feedback and contributions from the community.

It is common for a web page to include links which help visitors discover related pages on other sites. When a link ceases to work (e.g., because the page that it is pointing to either no longer exists or has been moved), users could rely on an archived copy of the linked page. However, due to the incompleteness of web archives, a sizeable fraction of dead links have no archived copies.

Low interaction response times are crucial to the experience that mobile apps provide for their users. Unfortunately, existing strategies to alleviate the network latencies that hinder app responsiveness fall short in practice. In particular, caching is plagued by challenges in setting expiration times that match when a resource's content changes, while prefetching hinges on accurate predictions of user behavior that have proven elusive. We present Marauder, a system that synergizes caching and prefetching to improve the speedups achieved by each technique while avoiding their inherent limitations. Key to Marauder is our observation that, like web pages, apps handle interactions by downloading and parsing structured text resources that entirely list (i.e., without needing to consult app binaries) the set of other resources to load. Building on this, Marauder introduces two low-risk optimizations directly from the app's cache. First, guided by cached text files, Marauder prefetches referenced resources during an already-triggered interaction. Second, to improve the efficacy of cached content, Marauder judiciously prefetches about-to-expire resources, extending cache lives for unchanged resources, and downloading updates for lightweight (but crucial) text files. Across a wide range of apps, live networks, interaction traces, and phones, Marauder reduces median and 90th percentile interaction response times by 27.4% and 43.5%, while increasing data usage by only 18%.

Many systems rely on traceroutes to monitor or characterize the Internet. The quality of the systems' inferences depends on the completeness and freshness of the traceroutes, but the refreshing of traceroutes is constrained by limited resources at vantage points. Previous approaches predict which traceroutes are likely out-of-date in order to allocate measurements, or monitor BGP feeds for changes that overlap traceroutes. Both approaches miss many path changes for reasons including the difficulty in predicting changes and the coarse granularity of BGP paths.

Online services all seek to provide their customers with the best Quality of Experience (QoE) possible. Milliseconds of delay can cause users to abandon a cat video or move onto a different shopping site, which translates into lost revenue. Thus, minimizing latency between users and content is crucial. To reduce latency, content and cloud providers have built massive, global networks. However, their networks must interact with customer ISPs via BGP, which has no concept of performance.

Web services that enable users in multiple regions to collaborate can increase availability and decrease latency by replicating data across data centers. If such a service spreads its data across multiple cloud providers---for the associated performance, cost, and reliability benefits---it cannot rely on cloud providers to keep the data globally consistent.

The existing slowness of the web on mobile devices frustrates users and hurts the revenue of website providers. Prior studies have attributed high page load times to dependencies within the page load process: network latency in fetching a resource delays its processing, which in turn delays when dependent resources can be discovered and fetched.

Large content providers build points of presence around the world, each connected to tens or hundreds of networks. Ideally, this connectivity lets providers better serve users, but providers cannot obtain enough capacity on some preferred peering paths to handle peak traffic demands. These capacity constraints, coupled with volatile traffic and performance and the limitations of the 20 year old BGP protocol, make it difficult to best use this connectivity.

User surveys have shown that a typical user has over a 100 apps on his/her smartphone [1], but stops using many of them. We conduct a user study to identify such unused apps, which we call zombies, and show via experiments that zombie apps consume significant resources on a user's smartphone and access his/her private information. We then design and build ZapDroid, which enables users to detect and silo zombie apps in an effective way to prevent their undesired activities. If and when the user wishes to resume using such an app, ZapDroid restores the app quickly and effectively. Our evaluations show that: (i) ZapDroid saves twice the energy from unwanted zombie app behaviors as compared to apps from the Play Store that kill background unwanted processes, and (ii) it effectively prevents zombie apps from using undesired permissions. In addition, ZapDroid is energy-efficient, consuming <;4 percent of the battery per day.

Images/videos are often uploaded in situations like disasters. This can tax the network in terms of increased load and thereby upload latency, and this can be critical for response activities. In such scenarios, prior work has shown that there is significant redundancy in the content (e.g., similar photos taken by users) transferred. By intelligently suppressing/deferring transfers of redundant content, the load can be significantly reduced, thereby facilitating the timely delivery of unique, possibly critical information. A key challenge here however, is detecting “what content is similar,” given that the content is generated by uncoordinated user devices. Toward addressing this challenge, we propose a framework, wherein a service to which the content is to be uploaded first solicits metadata (e.g., image features) from any device uploading content. By intelligently comparing this metadata with that associated with previously uploaded content, the service effectively identifies (and thus enables the suppression of) redundant content. Our evaluations on a testbed of 20 Android smartphones and via ns3 simulations show that we can identify similar content with a 70% true positive rate and a 1% false positive rate. The resulting reduction in redundant content transfers translates to a latency reduction of 44 % for unique content.

Today, many smartphone users are unaware of what applications (apps) they should stop using to prevent their battery from running out quickly. The problem is identifying such apps is hard due to the fact that there exist hundreds of thousands of apps and their impact on the battery is not well understood. We show via extensive measurement studies that the impact of an app on battery consumption depends on both environmental (wireless) factors and usage patterns. Based on this, we argue that there exists a critical need for a tool that allows a user to: 1) identify apps that are energy hungry and 2) understand why an app is consuming energy, on her phone. Toward addressing this need, we present TIDE, a tool to detect high energy apps on any particular smartphone. TIDE's key characteristic is that it accounts for usage-centric information while identifying energy hungry apps from among a multitude of apps that run simultaneously on a user's phone. Our evaluation of TIDE on a test bed of Android-based smartphones, using week-long smartphone usage traces from 17 real users, shows that TIDE correctly identifies over 94% of energy-hungry apps and has a false positive rate of <; 6%.

This paper presents the Online Social Network Investigator (OSNI), a scalable distributed system to search social net- work data, based on a spatiotemporal window and a list of keywords. Given that only 2% of tweets are geolocated, we have implemented and compared various state-of-art loca- tion estimation techniques. Further, to enrich the context of posts, associations of images to terms are estimated through various classication techniques. The accuracies of these es- timations are evaluated on large real datasets. OSNI's query interface is available on the Web.

Services offered by cloud providers (e.g., for key-value storage and for redirecting clients to nearby data centers) simplify the development of applications deployed in the cloud. However, since any cloud provider’s service offerings are far from complete, many cloud providers host a service marketplace, wherein third parties can advertise new services.

Despite the popularity of recommendation services (such as Yelp, Healthgrades, and Angie’s List), for a majority of entities listed on these services, one has to rely on opinions shared by a few users. We argue that this paucity of reviews for most entities stems from the fact that the vast majority of users largely consume opinions shared by others but seldom post reviews themselves. Therefore, leveraging the trend that services are increasingly accessed from a client-side app rather than over the Web, we propose augmenting recommendation services to implicitly infer any user’s opinions based on observations of the user’s activities. Implicit inference of many of a user’s recommendations are feasible due to the rich sensory capabilities of smartphones and wearables as well as the digital footprints left behind by many activities in the physical world. However, implicit inference of opinions is inherently uncertain and automated sharing of inferences raises significant privacy and security concerns. In this paper, we discuss how to tackle these challenges so that users looking for recommendations can draw upon a more comprehensive set of opinions than is the case today.

With 20 million installs a day , third-party apps are a major reason for the popularity and addictiveness of Facebook. Unfortunately, hackers have realized the potential of using apps for spreading malware and spam. The problem is already significant, as we find that at least 13% of apps in our dataset are malicious. So far, the research community has focused on detecting malicious posts and campaigns. In this paper, we ask the question: Given a Facebook application, can we determine if it is malicious? Our key contribution is in developing FRAppE-Facebook's Rigorous Application Evaluator-arguably the first tool focused on detecting malicious apps on Facebook. To develop FRAppE, we use information gathered by observing the posting behavior of 111K Facebook apps seen across 2.2 million users on Facebook. First, we identify a set of features that help us distinguish malicious apps from benign ones. For example, we find that malicious apps often share names with other apps, and they typically request fewer permissions than benign apps. Second, leveraging these distinguishing features, we show that FRAppE can detect malicious apps with 99.5% accuracy, with no false positives and a high true positive rate (95.9%). Finally, we explore the ecosystem of malicious Facebook apps and identify mechanisms that these apps use to propagate. Interestingly, we find that many apps collude and support each other; in our dataset, we find 1584 apps enabling the viral propagation of 3723 other apps through their posts. Long term, we see FRAppE as a step toward creating an independent watchdog for app assessment and ranking, so as to warn Facebook users before installing apps.

Developers of cloud-connected mobile apps need to ensure the consistency of application and user data across multiple devices. Mobile apps demand different choices of distributed data consistency under a variety of usage scenarios. The apps also need to gracefully handle intermittent connectivity and disconnections, limited bandwidth, and client and server failures. The data model of the apps can also be complex, spanning inter-dependent structured and unstructured data, and needs to be atomically stored and updated locally, on the cloud, and on other mobile devices.

User surveys have shown that a typical user has over a hundred apps on her smartphone [1], but stops using many of them. We conduct a user study to identify such unused apps, which we call zombies, and show via experiments that zombie apps consume significant resources on a user's smartphone and access her private information. We then design and build ZapDroid, which enables users to detect and silo zombie apps in an effective way to prevent their undesired activities. If and when the user wishes to resume using such an app, ZapDroid restores the app quickly and effectively. Our evaluations show that: (i) ZapDroid saves twice the energy from unwanted zombie app behaviors as compared to apps from the Play Store that kill background unwanted processes, and (ii) it effectively prevents zombie apps from using undesired permissions. In addition, ZapDroid is energ-efficient, consuming < 4% of the battery per day.

Today, many smartphone users are unaware of what applications (apps) they should stop using to prevent their battery from running out quickly. The problem is identifying such apps is hard due to the fact that there exist hundreds of thousands of apps and their impact on the battery is not well understood. We show via extensive measurement studies that the impact of an app on battery consumption depends on both environmental (wireless) factors and usage patterns. Based on this, we argue that there exists a critical need for a tool that allows a user to (a) identify apps that are energy hungry, and (b) understand why an app is consuming energy, on her phone. Towards addressing this need, we present TIDE, a tool to detect high energy apps on any particular smartphone. TIDE's key characteristic is that it accounts for usage-centric information while identifying energy hungry apps from among a multitude of apps that run simultaneously on a user's phone. Our evaluation of TIDE on a testbed of Android-based smartphones, using weeklong smartphone usage traces from 17 real users, shows that TIDE correctly identifies over 94% of energy-hungry apps and has a false positive rate of <; 6%.

The Bring-Your-Own-Handheld-device (BYOH) phenomenon continues to make inroads as more people bring their own handheld devices to work or school. While convenient to device owners, this trend presents novel management challenges to network administrators. Prior efforts only focused on studying either the comparative characterization of aggregate network traffic between BYOHs and non-BYOHs or network performance issues, such as TCP and download times or mobility issues. We identify one critical question that network administrators need to answer: how do these BYOHs behave individually? In response, we design and deploy Brofiler, a behavior-aware profiling framework that improves visibility into the management of BYOHs. The contributions of our work are two-fold. First, we present Brofiler, a time-aware device-centric approach for grouping devices into intuitive behavioral groups. Second, we conduct an extensive study of BYOHs using our approach with real data collected over a year, and highlight several novel insights on the behavior of BYOHs. These observations underscore the importance of that BYOHs need to be managed explicitly as they behave in unique and unexpected ways.

To reduce page load times and bandwidth usage for mobile web browsing, middleboxes that compress page content are commonly used today. Unfortunately, this can hurt performance in many cases; via an extensive measurement study, we show that using middleboxes to facilitate compression results in up to 28% degradation in page load times when the client enjoys excellent wireless link conditions. We find that benefits from compression are primarily realized under bad network conditions. Guided by our study, we design and implement FlexiWeb, a framework that determines both when to use a middlebox and how to use it, based on the client's network conditions. First, FlexiWeb selectively fetches objects on a web page either directly from the source or via a middlebox, rather than fetching all objects via the middlebox. Second, instead of simply performing lossless compression of all content, FlexiWeb performs network-aware compression of images by selecting from among a range of content transformations. We implement and evaluate a prototype of FlexiWeb using Google's open source Chromium mobile browser and our implementation of a modified version of Google's open source compression proxy. Our extensive experiments show that, across a range of scenarios, FlexiWeb reduces page load times for mobile clients by 35-42% compared to the status quo.

Every night, many smartphones are plugged into a power source for recharging the battery. Given the increasing computing capabilities of smartphones, these idle phones constitute a sizeable computing infrastructure. Therefore, for an enterprise which supplies its employees with smartphones, we argue that a computing infrastructure that leverages idle smartphones being charged overnight is an energy-efficient and cost-effective alternative to running certain tasks on traditional servers. While parallel execution models and schedulers exist for servers, smartphones face a unique set of technical challenges due to the heterogeneity in CPU clock speed, variability in network bandwidth, and lower availability than servers. In this paper, we address many of these challenges to develop CWC-a distributed computing infrastructure using smartphones. We implement and evaluate a prototype of CWC that employs a novel scheduling algorithm to minimize the makespan of a set of computing tasks. Our evaluations using a testbed of 18 Android phones show that CWC's scheduler yields a makespan that is 1.6× faster than other simpler approaches.

Images/videos are often uploaded in situations like disasters. This can tax the network in terms of increased load and thereby upload latency, and this can be critical for response activities. In such scenarios, prior work has shown that there is significant redundancy in the content (e.g., similar photos taken by users) transferred. By intelligently suppressing/deferring transfers of redundant content, the load can be significantly reduced, thereby facilitating the timely delivery of unique, possibly critical information. A key challenge here however, is detecting 'what content is similar,' given that the content is generated by uncoordinated user devices. Towards addressing this challenge, we propose a framework, wherein a service to which the content is to be uploaded first solicits metadata (e.g, image features) from any device uploading content. By intelligently comparing this metadata with that associated with previously uploaded content, the service effectively identifies (and thus enables the suppression of) redundant content. Our evaluations on a testbed of 20 Android smartphones and via ns3 simulations show that we can identify similar content with a 70% true positive rate and a 1% false positive rate. The resulting reduction in redundant content transfers translates to a latency reduction of 44 % for unique content.

Though the widely used Tor anonymity network is designed to enable low-latency anonymous communication, interactive communications on Tor incur latencies over 5 × greater than on the direct Internet path, and in many cases, autonomous systems (ASs) can compromise anonymity via correlations of network traffic. In this paper, we develop LASTor, a new Tor client that addresses these shortcomings in Tor with only client-side modifications. First, LASTor improves communication latencies by accounting for the inferred locations of Tor relays while choosing paths. Since the preference for shorter paths reduces the entropy of path selection, we design LASTor so that a user can choose an appropriate tradeoff between latency and anonymity. Second, we develop an efficient and accurate algorithm to identify paths on which an AS can compromise anonymity by traffic correlation. LASTor avoids such paths to improve a user's anonymity, and the low runtime of the algorithm ensures that the impact on end-to-end communication latencies is low. Our results show that, in comparison to the default Tor client, LASTor reduces median latencies by 25% while also reducing the false negative rate of not detecting a potential snooping AS from 57% to 11%.

Over the years, the Web has evolved from simple text content from one server to a complex ecosystem with different types of content from servers spread across several administrative domains. There is anecdotal evidence of users being frustrated with high page load times. Because page load times are known to directly impact user satisfaction, providers would like to understand if and how the complexity of their Web sites affects the user experience. While there is an extensive literature on measuring Web graphs, Web site popularity, and the nature of Web traffic, there has been little work in understanding how complex individual Web sites are, and how this complexity impacts the clients' experience. This paper is a first step to address this gap. To this end, we identify a set of metrics to characterize the complexity of Web sites both at a content level (e.g., number and size of images) and service level (e.g., number of servers/origins). We find that the distributions of these metrics are largely independent of a Web site's popularity rank. However, some categories (e.g., News) are more complex than others. More than 60% of Web sites have content from at least five non-origin sources, and these contribute more than 35% of the bytes downloaded. In addition, we analyze which metrics are most critical for predicting page render and load times and find that the number of objects requested is the most important factor. With respect to variability in load times, however, we find that the number of servers is the best indicator.

Computing-as-a-service has been evolving steadily. Today, private clouds (e.g., Google's internal shared computing cluster) as well as public clouds (e.g., Amazon's web services (AWS), Microsoft's Azure) provide computing abstractions at various levels: bare virtual machines, specialized languages and runtimes (e.g., for massively-parallel data processing---MapReduce, Dryad), web services. For example, Amazon offers bare virtual machines as well as MapReduce clusters.

On today's online social networks, a user can discover only those recommendations that her friends put in the effort to share. Therefore, we present the PullRec framework for enabling users to pull recommendations from their friends. PullRec employs two measures to minimize the effort involved in sharing recommendations. First, to reduce the onus on users to express their recommendations, PullRec proactively logs all the entities about which a user may have an opinion and attempts to infer the user's opinions. Second, to ensure that users are not spammed with irrelevant queries, when a user queries for recommendations on a certain topic, PullRec notifies only those friends of the user who are likely to have relevant recommendations. PullRec is a step towards enabling a user to discover all recommendations that her friends are willing to share with her.

Existing cloud computing platforms leave it up to applications to deal with the complexities associated with data replication and propagation across data centers. In our work, we propose the CSPAN key-value store to instead export a unified view of storage services in several geographically distributed data centers. To minimize the cost incurred by application providers, we combine two principles. First, CSPAN spans the data centers of multiple cloud providers. Second, CSPAN judiciously trades off the lower latencies and the higher storage and data propagation costs based on an application's anticipated workload, latency goals, and consistency requirements.

By offering storage services in several geographically distributed data centers, cloud computing platforms enable applications to offer low latency access to user data. However, application developers are left to deal with the complexities associated with choosing the storage services at which any object is replicated and maintaining consistency across these replicas.

Online social networks (OSNs) have become a popular new vector for distributing malware and spam, which we refer to as socware. Unlike email spam, which is sent by spammers directly to intended victims, socware cascades through OSNs as compromised users spread it to their friends. In this paper, we analyze data from the walls of roughly 3 million Facebook users over five months, with the goal of developing a better understanding of socware cascades.

We present TritonSort, a highly efficient, scalable sorting system. It is designed to process large datasets, and has been evaluated against as much as 100TB of input data spread across 832 disks in 52 nodes at a rate of 0.938TB/min. When evaluated against the annual Indy GraySort sorting benchmark, TritonSort is 66% better in absolute performance and has over six times the per-node throughput of the previous record holder. When evaluated against the 100TB Indy JouleSort benchmark, TritonSort sorted 9703 records/Joule. In this article, we describe the hardware and software architecture necessary to operate TritonSort at this level of efficiency. Through careful management of system resources to ensure cross-resource balance, we are able to sort data at approximately 80% of the disks’ aggregate sequential write speed. We believe the work holds a number of lessons for balanced system design and for scale-out architectures in general. While many interesting systems are able to scale linearly with additional servers, per-server performance can lag behind per-server capacity by more than an order of magnitude. Bridging the gap between high scalability and high performance would enable either significantly less expensive systems that are able to do the same work or provide the ability to address significantly larger problem sets with the same infrastructure.

User privacy has been an increasingly growing concern in online social networks (OSNs). While most OSNs today provide some form of privacy controls so that their users can protect their shared content from other users, these controls are typically not sufficiently expressive and/or do not provide fine-grained protection of information. In this paper, we consider the introduction of a new privacy control---group messaging on Twitter, with users having fine-grained control over who can see their messages. Specifically, we demonstrate that such a privacy control can be offered to users of Twitter today without having to wait for Twitter to make changes to its system. We do so by designing and implementing Twitsper, a wrapper around Twitter that enables private group communication among existing Twitter users while preserving Twitter's commercial interests. Our design preserves the privacy of group information (i.e., who communicates with whom) both from the Twitsper server as well as from undesired Twitsper users. Furthermore, our evaluation shows that our implementation of Twitsper imposes minimal server-side bandwidth requirements and incurs low client-side energy consumption. Our Twitsper client for Android-based devices has been downloaded by over 1000 users and its utility has been noted by several media articles.

Every night, a large number of idle smartphones are plugged into a power source for recharging the battery. Given the increasing computing capabilities of smartphones, these idle phones constitute a sizeable computing infrastructure. Therefore, for an enterprise which supplies its employees with smartphones, we argue that a computing infrastructure that leverages idle smartphones being charged overnight is an energy-efficient and cost-effective alternative to running tasks on traditional server infrastructure. While parallel execution and scheduling models exist for servers (e.g., MapReduce), smartphones present a unique set of technical challenges due to the heterogeneity in CPU clock speed, variability in network bandwidth, and lower availability compared to servers.

With 20 million installs a day, third-party apps are a major reason for the popularity and addictiveness of Facebook. Unfortunately, hackers have realized the potential of using apps for spreading malware and spam. The problem is already significant, as we find that at least 13% of apps in our dataset are malicious. So far, the research community has focused on detecting malicious posts and campaigns.

The Internet was designed to always find a route if there is a policy-compliant path. However, in many cases, connectivity is disrupted despite the existence of an underlying valid path. The research community has focused on short-term outages that occur during route convergence. There has been less progress on addressing avoidable long-lasting outages. Our measurements show that long-lasting events contribute significantly to overall unavailability.

The widely used Tor anonymity network is designed to enable low-latency anonymous communication. However, in practice, interactive communication on Tor-which accounts for over 90% of connections in the Tor network [1]-incurs latencies over 5x greater than on the direct Internet path. In addition, since path selection to establish a circuit in Tor is oblivious to Internet routing, anonymity guarantees can breakdown in cases where an autonomous system (AS) can correlate traffic across the entry and exit segments of a circuit. In this paper, we show that both of these shortcomings in Tor can be addressed with only client-side modifications, i.e., without requiring a revamp of the entire Tor architecture. To this end, we design and implement a new Tor client, LASTor. First, we show that LASTor can deliver significant latency gains over the default Tor client by simply accounting for the inferred locations of Tor relays while choosing paths. Second, since the preference for low latency paths reduces the entropy of path selection, we design LASTor's path selection algorithm to be tunable. A user can choose an appropriate tradeoff between latency and anonymity by specifying a value between 0 (lowest latency) and 1 (highest anonymity) for a single parameter. Lastly, we develop an efficient and accurate algorithm to identify paths on which an AS can correlate traffic between the entry and exit segments. This algorithm enables LASTor to avoid such paths and improve a user's anonymity, while the low runtime of the algorithm ensures that the impact on end-to-end latency of communication is low. By applying our techniques to measurements of real Internet paths and by using LASTor to visit the top 200 websites from several geographically-distributed end-hosts, we show that, in comparison to the default Tor client, LASTor reduces median latencies by 25% while also reducing the false negative rate of not detecting a potential snooping AS from 57% to 11%.

Landmark-based routing (LR) provides a promising approach for scalable point-to-point routing in wireless sensor networks (WSNs). Though various approaches have been proposed for landmark-based routing, they either introduce significant computational complexity or are inefficient in realistic, dynamic environments. In this paper, we identify three design principles that could form the basis of efficiency: algorithmic simplicity, update efficiency, and application awareness. Motivated by these principles, we present XLR, a new, flexible and comprehensive framework that tackles the inefficiency of landmark-based routing. XLR consists of four components: Relay Selection (RS), Parametric P-Norm distance function (PPN), Efficient Update with Coordinate Difference (EUCD) and General Forwarding (GF). The key advantage of XLR is that any subset of XLR's components can be independently incorporated into most landmark-based routing protocols.We perform extensive simulations to demonstrate that: (i) RS, a simple method, yields good performance comparable with previous methods, (ii) PPN increases LR performance considerably, (iii) EUCD reduces coordinate update overhead by up to 39%, and (iv) our GF outperforms previous approaches that consider factors such as link quality, delay and power consumption independently.

Over the years, the web has evolved from simple text content from one server to a complex ecosystem with different types of content from servers spread across several administrative domains. There is anecdotal evidence of users being frustrated with high page load times or when obscure scripts cause their browser windows to freeze. Because page load times are known to directly impact user satisfaction, providers would like to understand if and how the complexity of their websites affects the user experience.

Operators and researchers want accurate router-level views of the Internet for purposes including troubleshooting and modeling. However, tools such as traceroute return IP addresses. Because routers may have dozens of IP addresses, or aliases, multiple measurements may return different addresses, obscuring whether they represent the same machine. While many techniques exist to address this issue by identifying some IP aliases, these techniques, even in combination, find only a subset of alias pairs. To improve this state, we design and evaluate a new alias resolution technique using the IP prespecified timestamp option. This option allows a sender to request timestamp val- ues from multiple IP addresses in the same probe. By careful arrangement of these IP addresses, we show that we can infer aliases in many cases. In this paper, we conduct a measurement study of how many routers support IP timestamps, demonstrating that enough honor the option to base our technique on it. Using our technique, and compared to the most accurate alias information available, we find that 94.7% of the aliases identified by our technique are true positives. Further, we show that our IP timestamp-based technique complements existing alias resolution techniques, providing significant gains by discovering previously unidentifiable aliases.

Today's mobile networks prevent users from freely accessing all available networks. Instead, seamless network composition could present a win-win situation for both users and operators. Users can gain better quality of service with more resources to choose from, while each individual operator can provision lesser bandwidth since resources can be shared during times of peak demand. In this paper, we analyze the benefits of operator cooperation using real trace data of cellular data access. We leverage the difference in burstiness at small timescales across network providers to shed the peak usage of one operator on to another. Our results show that even when an operator provisions network capacity below the peak load, cooperation with other network providers can help maintain quality of service for most sessions. In addition, we investigate the performance delivered by various kinds of cellular data cards. Our results confirm that WiFi 802.11b/g consistently delivers superior performance compared to 3G. It will take the next generation 4G technologies such as LTE to deliver end-user performance comparable to widely-deployed 802.11 networks.

Replicating content across a geographically distributed set of servers and redirecting clients to the closest server in terms of latency has emerged as a common paradigm for improving client performance. In this paper, we analyze latencies measured from servers in Google's content distribution network (CDN) to clients all across the Internet to study the effectiveness of latency-based server selection. Our main result is that redirecting every client to the server with least latency does not suffice to optimize client latencies. First, even though most clients are served by a geographically nearby CDN node, a sizeable fraction of experience latencies several tens of milliseconds higher than other in the same region. Second, we find that queueing delays often override the benefits of a client interacting with a nearby server.

Several models have been recently proposed for predicting the latency of end to end Internet paths. These models treat the Internet as a black-box, ignoring its internal structure. While these models are simple, they can often fail systematically; for example, the most widely used models use metric embeddings that predict no benefit to detour routes even though half of all Internet routes can benefit from detours.In this paper, we adopt a structural approach that predicts path latency based on measurements of the Internet's routing topology, PoP connectivity, and routing policy. We find that our approach outperforms Vivaldi, the most widely used black-box model. Furthermore, unlike metric embeddings, our approach successfully predicts 65% of detour routes in the Internet. The number of measurements used in our approach is comparable with that required by black box techniques, but using traceroutes instead of pings.

Web performance measurements and availability tests have been carried out using a variety of infrastructures over the last several years. Disruptions in the Internet can lead to Web sites being unavailable or increase user-perceived latency. The unavailability could be due to DNS, failures in segments of the physical network cutting off thousands of users, or attacks. Prompt reactions to network-wide events can be facilitated by local or remote measurement and monitoring. Better yet, a distributed set of intercommunicating measurement and monitoring entities that react to events dynamically could go a long way to handle disruptions.We have designed and built ATMEN, a triggered measurement infrastructure to communicate and coordinate across various administrative entities. ATMEN nodes can trigger new measurements, query ongoing passive measurements or historical measurements stored on remote nodes, and coordinate the responses to make local decisions. ATMEN reduces wasted measurements by judiciously reusing measurements along three axes: spatial, temporal, and application.We describe the use of ATMEN for key Web applications such as performance based ranking of popular Web sites and availability of DNS servers on which most Web transactions are dependent. The evaluation of ATMEN is done using multiple network monitoring entities called Gigascopes installed across the USA, measurement data of a popular network application involving millions of users distributed across the Internet, and scores of clients to aid in gathering measurement information upon demand. Our results show that such a system can be built in a scalable fashion.

We present a novel heuristic algorithm for routing and wavelength assignment in virtual-wavelength-path (VWP) routed wavelength-division multiplexed optical networks. We are the first to take up the approach of both minimizing the network cost, as well as maximizing the resource utilization. Our algorithm not only minimizes the number of wavelengths required for supporting the given traffic demand on any given topology, but also aims to minimize the mean hop length of all the lightpaths which in turn maximizes the resource utilization. The algorithm initially assigns the minimum hop path to each route and then performs efficient rerouting to reduce the number of wavelengths required while also trying to minimize the average hop length. To further reduce the network cost, we also propose a wavelength assignment procedure for VWP routed networks which minimizes the number of wavelength converters required. Our algorithm has been tested on various topologies for different types of traffic demands and has been found to give solutions much better than previous standards for this problem.