AT&T Labs

About: AT&T Labs is a based out in . It is known for research contribution in the topics: Network packet & The Internet. The organization has 1879 authors who have published 5595 publications receiving 483151 citations.

Revisiting Route Caching: The World Should Be Flat

Abstract: Internet routers' forwarding tables (FIBs), which must be stored in expensive fast memory for high-speed packet forwarding, are growing quickly in size due to increased multihoming, finer-grained traffic engineering, and deployment of IPv6 and VPNs. To address this problem, several Internet architectures have been proposed to reduce FIB size by returning to the earlier approach of route caching : storing only the working set of popular routes in the FIB. This paper revisits route caching. We build upon previous work by studying flat, uni-class (/24) prefix caching, with modern traffic traces from more than 60 routers in a tier-1 ISP. We first characterize routers' working sets and then evaluate route-caching performance under different cache replacement strategies and cache sizes. Surprisingly, despite the large number of deaggregated /24 subnets, caching uni-class prefixes can effectively curb the increase of FIB sizes. Moreover, uni-class prefixes substantially simplify a cache design by eliminating longest-prefix matching, enabling FIB design with slower memory technologies. Finally, by comparing our results with previous work, we show that the distribution of traffic across prefixes is becoming increasingly skewed, making route caching more appealing.

The First Surface Realisation Shared Task: Overview and Evaluation Results

Abstract: The Surface Realisation (SR) Task was a new task at Generation Challenges 2011, and had two tracks: (1) Shallow: mapping from shallow input representations to realisations; and (2) Deep: mapping from deep input representations to realisations. Five teams submitted six systems in total, and we additionally evaluated human toplines. Systems were evaluated automatically using a range of intrinsic metrics. In addition, systems were assessed by human judges in terms of Clarity, Readability and Meaning Similarity. This report presents the evaluation results, along with descriptions of the SR Task Tracks and evaluation methods. For descriptions of the participating systems, see the separate system reports in this volume, immediately following this results report.

Use of a P3P user agent by early adopters

Abstract: The Platform for Privacy Preferences (P3P), developed by the World Wide Web Consortium (W3C), provides a standard computer-readable format for privacy policies and a protocol that enables web browsers to read and process privacy policies automatically. P3P enables machine-readable privacy policies that can be retrieved automatically by web browsers and other user agent tools that can display symbols, prompt users, or take other appropriate actions. We developed the AT&T Privacy Bird as a P3P user agent that can compare P3P policies against a user's privacy preferences. Since P3P was adopted as a W3C recommendation in April 2002, little work has been done to study how it is being used and, especially, its impact on users. Many questions have been raised about whether and how Internet users will make use of P3P, and how to build P3P user agents that will prove most useful to end users. In this paper we first provide a brief introduction to P3P and the AT&T Privacy Bird. Then we discuss a survey of AT&T Privacy Bird users that we conducted in August 2002. We found that a large proportion of AT&T Privacy Bird users began reading privacy policies more often and being more proactive about protecting their privacy as a result of using this software. Unfortunately, the usefulness of P3P user agents is severely limited by the number of web sites that have implemented P3P. Our survey results also suggest that if it becomes easier to compare privacy policy across e-commerce web sites, a significant group of consumers would likely use this information in their purchase decisions.

Factor-covering designs for testing software

Abstract: Testing is a critical component of modern software development. The problem of designing a suite of test cases is superficially similar to that of designing an experiment to estimate main effects and interactions, but there are crucial differences. Additive models are unhelpful, and classical design criteria are also. We propose a new class of models and new measures of effectiveness. We compare several designs.

MP-DASH: Adaptive Video Streaming Over Preference-Aware Multipath

Abstract: Compared with using only a single wireless path such as WiFi, leveraging multipath (e.g., WiFi and cellular) can dramatically improve users' quality of experience (QoE) for mobile video streaming. However, Multipath TCP (MPTCP), the de-facto multipath solution, lacks the support to prioritize one path over another. When applied to video streaming, it may cause undesired network usage such as substantial over-utilization of the metered cellular link. In this paper, we propose MP-DASH, a multipath framework for video streaming with the awareness of network interface preferences from users. The basic idea behind MP-DASH is to strategically schedule video chunks' delivery and thus satisfy user preferences. MP-DASH can work with a wide range of off-the-shelf video rate adaptation algorithms with very small changes. Our extensive field studies at 33 locations in three U.S. states suggest that MP-DASH is very effective: it can reduce cellular usage by up to 99% and radio energy consumption by up to 85% with negligible degradation of QoE, compared with off-the-shelf MPTCP.