In-Flight Communication (IFC), available on a growing number of commercial flights, is often received by consumers with both awe for its mere availability and harsh criticism for its poor performance. Indeed, IFC provides Internet connectivity in some of the most challenging conditions with aircraft traveling at speeds in excess of 500 mph at 30,000 feet above the ground. Yet, while existing services do provide basic Internet \em accessibility, anecdotal reports rank their quality of service as, at best, poor. In this paper, we present the first characterization of deployed IFC systems. Using over 45 flight-hours of measurements, we profile the performance of IFC across the two dominant access technologies -- direct air-to-ground communication (DA2GC) and mobile satellite service (MSS). We show that IFC QoS is in large part determined by the high latencies inherent to DA2GC and MSS, with RTTs averaging 200ms and 750ms, respectively, and that these high latencies directly impact the performance of common applications such as web browsing. While each IFC technology is based on well studied wireless communication technologies, our findings reveal that IFC links experience further degraded link performance than their technological antecedents. We find median loss rates of 7%, and nearly 40% loss at the 90th percentile for MSS, 6.8x larger than recent characterizations of residential satellite networks. We extend our IFC study exploring the potential of the newly released HTTP/2 and QUIC protocols in an emulated IFC environment, finding that QUIC is able to improve page load times by as much as 7.9 times. In addition, we find that HTTP/2»s use of multiplexing multiple requests onto a single TCP connection performs up to 4.8x \em worse than HTTP/1.1 when faced with large numbers of objects. We use network emulation to explore proposed technological improvements to existing IFC systems finding that high link losses, and not bandwidth, account for the largest factor of performance degradation with applications such as web browsing.

Google's QUIC protocol, which implements TCP-like properties at the application layer atop a UDP transport, is now used by the vast majority of Chrome clients accessing Google properties but has no formal state machine specification, limited analysis, and ad-hoc evaluations based on snapshots of the protocol implementation in a small number of environments. Further frustrating attempts to evaluate QUIC is the fact that the protocol is under rapid development, with extensive rewriting of the protocol occurring over the scale of months, making individual studies of the protocol obsolete before publication.

Middleboxes implement a variety of network management policies (e.g., prioritizing or blocking traffic) in their networks. While such policies can be beneficial (e.g., blocking malware) they also raise issues of network neutrality and freedom of speech when used for application-specific differentiation and censorship. There is a poor understanding of how such policies are implemented in practice, and how they can be evaded efficiently. As a result, most circumvention solutions are brittle, point solutions based on manual analysis.

Traffic differentiation---giving better (or worse) performance to certain classes of Internet traffic---is a well-known but poorly understood traffic management policy. There is active discussion on whether and how ISPs should be allowed to differentiate Internet traffic, but little data about current practices to inform this discussion. Previous work attempted to address this problem for fixed line networks; however, there is currently no solution that works in the more challenging mobile environment.

The goal of this research is to detect traffic differentiation in cellular data networks. We define service differentiation as any attempt to change the performance of network traffic traversing an ISP's boundaries. ISPs may implement differentiation policies for a number of reasons, including load balancing, bandwidth management, or business reasons. Specifically, we focus on detecting whether certain types of network traffic receive better (or worse) performance. As an example, a wireless provider might limit the performance of third-party VoIP or video calling services (or any other competing services) by introducing delays or reducing transfer rates to encourage users to use services provided by the wireless provider. Previous work explored this problem in limited environments. Glasnost focused on BitTorrent in the desktop/laptop environment, and lacked the ability to conduct controlled experiments to provide strong evidence of differentiation. NetDiff covered a wide range of passively gathered traffic from a large ISP but likewise did not support targeted, controlled experiments. We address these limitations with Mobile Replay.

Web search is an integral part of our daily lives. Recently, there has been a trend of personalization in Web search, where different users receive different results for the same search query. The increasing personalization is leading to concerns about Filter Bubble effects, where certain users are simply unable to access information that the search engines' algorithm decides is irrelevant. Despite these concerns, there has been little quantification of the extent of personalization in Web search today, or the user attributes that cause it.

Online content ratings services allow users to find and share content ranging from news articles (Digg) to videos (YouTube) to businesses (Yelp). Generally, these sites allow users to create accounts, declare friendships, upload and rate content, and locate new content by leveraging the aggregated ratings of others. These services are becoming increasingly popular; Yelp alone has over 33 million reviews. Unfortunately, this popularity is leading to increasing levels of malicious activity, including multiple identity (Sybil) attacks and the "buying" of ratings from users.

The performance of receiver, transmitter, and joint transmitter/receiver antenna array processing for interference nulling and diversity over fading radio links are compared and contrasted in this paper. Specific examples of linear and non-linear algorithms are considered in this context. To perform transmitter processing, a priori knowledge of the radio propagation channel is required at the transmitter. This is typically achieved by the provision of a feedback loop that supplies the transmitter with the channel state information (CSI). The impact on transmitter processing of non-zero delays in the CSI feedback loop is quantified in this paper. It is assumed that channel estimation is performed with perfect accuracy at the receiver, and that the feedback loop is error-free. It is shown that while transmitter processing out performs receiver processing at low relative Doppler frequencies, its performance degrades rapidly when the CSI feedback delay is greater than 2% of the channel coherence time. The results presented can be readily interpreted in the context of multi-user uplink and downlink in cellular systems, or collaborative signal processing among base stations.