arXiv subjects

Aravindh Raman

Publications and source records attributed to Aravindh Raman.

16 recordsLinked to original sources

arXiv2025

Collaborative Content Moderation in the Fediverse

The Fediverse, a group of interconnected servers providing a variety of interoperable services (e.g. micro-blogging in Mastodon) has gained rapid popularity. This sudden growth, partly driven by Elon Musk's acquisition of Twitter, has created challenges for administrators though. This paper focuses on one particular challenge: content moderation, e.g. the need to remove spam or hate speech. While centralized platforms like Facebook and Twitter rely on automated tools for moderation, their dependence on massive labeled datasets and specialized infrastructure renders them impractical for decentralized, low-resource settings like the Fediverse. In this work, we design and evaluate FedMod, a collaborative content moderation system based on federated learning. Our system enables servers to exchange parameters of partially trained local content moderation models with similar servers, creating a federated model shared among collaborating servers. FedMod demonstrates robust performance on three different content moderation tasks: harmful content detection, bot content detection, and content warning assignment, achieving average per-server macro-F1 scores of 0.71, 0.73, and 0.58, respectively.

cs.SI↗

arXiv2024

Decentralised Moderation for Interoperable Social Networks: A Conversation-based Approach for Pleroma and the Fediverse

The recent development of decentralised and interoperable social networks (such as the "fediverse") creates new challenges for content moderators. This is because millions of posts generated on one server can easily "spread" to another, even if the recipient server has very different moderation policies. An obvious solution would be to leverage moderation tools to automatically tag (and filter) posts that contravene moderation policies, e.g. related to toxic speech. Recent work has exploited the conversational context of a post to improve this automatic tagging, e.g. using the replies to a post to help classify if it contains toxic speech. This has shown particular potential in environments with large training sets that contain complete conversations. This, however, creates challenges in a decentralised context, as a single conversation may be fragmented across multiple servers. Thus, each server only has a partial view of an entire conversation because conversations are often federated across servers in a non-synchronized fashion. To address this, we propose a decentralised conversation-aware content moderation approach suitable for the fediverse. Our approach employs a graph deep learning model (GraphNLI) trained locally on each server. The model exploits local data to train a model that combines post and conversational information captured through random walks to detect toxicity. We evaluate our approach with data from Pleroma, a major decentralised and interoperable micro-blogging network containing 2 million conversations. Our model effectively detects toxicity on larger instances, exclusively trained using their local post information (0.8837 macro-F1). Our approach has considerable scope to improve moderation in decentralised and interoperable social networks such as Pleroma or Mastodon.

cs.CY↗

arXiv2023

Dissecting the Performance of Satellite Network Operators

The rapid growth of satellite network operators (SNOs) has revolutionized broadband communications, enabling global connectivity and bridging the digital divide. As these networks expand, it is important to evaluate their performance and efficiency. This paper presents the first comprehensive study of SNOs. We take an opportunistic approach and devise a methodology which allows to identify public network measurements performed via SNOs. We apply this methodology to both M-Lab and RIPE public datasets which allowed us to characterize low level performance and footprint of up to 18 SNOs operating in different orbits. Finally, we identify and recruit paid testers on three popular SNOs (Starlink, HughesNet, and ViaSat) to evaluate the performance of popular applications like web browsing and video streaming.

cs.NI↗

arXiv2023

T3P: Demystifying Low-Earth Orbit Satellite Broadband

The Internet is going through a massive infrastructural revolution with the advent of low-flying satellite networks, 5/6G, WiFi7, and hollow-core fiber deployments. While these networks could unleash enhanced connectivity and new capabilities, it is critical to understand the performance characteristics to efficiently drive applications over them. Low-Earth orbit (LEO) satellite mega-constellations like SpaceX Starlink aim to offer broad coverage and low latencies at the expense of high orbital dynamics leading to continuous latency changes and frequent satellite hand-offs. This paper aims to quantify Starlink's latency and its variations and components using a real testbed spanning multiple latitudes from the North to the South of Europe. We identify tail latencies as a problem. We develop predictors for latency and throughput and show their utility in improving application performance by up to 25%. We also explore how transport protocols can be optimized for LEO networks and show that this can improve throughput by up to 115% (with only a 5% increase in latency). Also, our measurement testbed with a footprint across multiple locations offers unique trigger-based scheduling capabilities that are necessary to quantify the impact of LEO dynamics.

cs.NI↗

arXiv2023

Flocking to Mastodon: Tracking the Great Twitter Migration

The acquisition of Twitter by Elon Musk has spurred controversy and uncertainty among Twitter users. The move raised as many praises as concerns, particularly regarding Musk's views on free speech. As a result, a large number of Twitter users have looked for alternatives to Twitter. Mastodon, a decentralized micro-blogging social network, has attracted the attention of many users and the general media. In this paper, we track and analyze the migration of 136,009 users from Twitter to Mastodon. Our analysis sheds light on the user-driven pressure towards centralization in a decentralized ecosystem and identifies the strong influence of the social network in platform migration. We also characterize the activity of migrated users on both Twitter and Mastodon.

cs.SI↗

arXiv2023

Will Admins Cope? Decentralized Moderation in the Fediverse

As an alternative to Twitter and other centralized social networks, the Fediverse is growing in popularity. The recent, and polemical, takeover of Twitter by Elon Musk has exacerbated this trend. The Fediverse includes a growing number of decentralized social networks, such as Pleroma or Mastodon, that share the same subscription protocol (ActivityPub). Each of these decentralized social networks is composed of independent instances that are run by different administrators. Users, however, can interact with other users across the Fediverse regardless of the instance they are signed up to. The growing user base of the Fediverse creates key challenges for the administrators, who may experience a growing burden. In this paper, we explore how large that overhead is, and whether there are solutions to alleviate the burden. We study the overhead of moderation on the administrators. We observe a diversity of administrator strategies, with evidence that administrators on larger instances struggle to find sufficient resources. We then propose a tool, WatchGen, to semi-automate the process.

cs.SI↗

arXiv2023

Scheduling Inference Workloads on Distributed Edge Clusters with Reinforcement Learning

Many real-time applications (e.g., Augmented/Virtual Reality, cognitive assistance) rely on Deep Neural Networks (DNNs) to process inference tasks. Edge computing is considered a key infrastructure to deploy such applications, as moving computation close to the data sources enables us to meet stringent latency and throughput requirements. However, the constrained nature of edge networks poses several additional challenges to the management of inference workloads: edge clusters can not provide unlimited processing power to DNN models, and often a trade-off between network and processing time should be considered when it comes to end-to-end delay requirements. In this paper, we focus on the problem of scheduling inference queries on DNN models in edge networks at short timescales (i.e., few milliseconds). By means of simulations, we analyze several policies in the realistic network settings and workloads of a large ISP, highlighting the need for a dynamic scheduling policy that can adapt to network conditions and workloads. We therefore design ASET, a Reinforcement Learning based scheduling algorithm able to adapt its decisions according to the system conditions. Our results show that ASET effectively provides the best performance compared to static policies when scheduling over a distributed pool of edge resources.

cs.LG↗

arXiv2022

Design and Evaluation of IPFS: A Storage Layer for the Decentralized Web

Recent years have witnessed growing consolidation of web operations. For example, the majority of web traffic now originates from a few organizations, and even micro-websites often choose to host on large pre-existing cloud infrastructures. In response to this, the "Decentralized Web" attempts to distribute ownership and operation of web services more evenly. This paper describes the design and implementation of the largest and most widely used Decentralized Web platform - the InterPlanetary File System (IPFS) - an open-source, content-addressable peer-to-peer network that provides distributed data storage and delivery. IPFS has millions of daily content retrievals and already underpins dozens of third-party applications. This paper evaluates the performance of IPFS by introducing a set of measurement methodologies that allow us to uncover the characteristics of peers in the IPFS network. We reveal presence in more than 2700 Autonomous Systems and 152 countries, the majority of which operate outside large central cloud providers like Amazon or Azure. We further evaluate IPFS performance, showing that both publication and retrieval delays are acceptable for a wide range of use cases. Finally, we share our datasets, experiences and lessons learned.

cs.NI↗

arXiv2022

DSM-MoC as Baseline: Reliability Assurance via Redundant Cellular Connectivity in Connected Cars

Connected Cars (CCs) and vehicle-to-everything (V2X) use cases require stringent reliability for safety and non-safety uses. With increasing network softwarisation, it has become easier to use multiple, redundant connectivity options instead of relying on a single network connectivity. But where should these redundant connections be managed? Is it at a network provider's core network - i.e. supply side managed (SSM) - or at the CC - i.e. demand side managed (DSM)? In our work, we investigate the use of SSM and DSM for CCs on four separate days and across 800 kilometers of major / minor roads in South East England. For Day 1, we captured performance indicators, and determined hypothetical multi-operator configurations for four UK providers and a global Universal SIM. For Day 2, 3& 4, we built and deployed a test-bed to actually implement network switching and understand performance (incl. for TCP & UDP) either on the road or in a stationary location. Based on our results, we make three contributions. First, we show that DSM can deliver superior performance for CCs more than any individual network (up to 28 percentage points in a hypothetical scenario), or SSM which had up to 4.8x longer page load times. Second, unlike other smartphone-only studies, our system-level study demonstrates that improvements of at least 12% can be obtained in a practical DSM field implementation for a CC. Third, we confirm that the advantage of DSM in a field implementation is higher for UDP traffic (23% better latency) compared to TCP (13%).

cs.NI↗

arXiv2022

Jettisoning Junk Messaging in the Era of End-to-End Encryption: A Case Study of WhatsApp

WhatsApp is a popular messaging app used by over a billion users around the globe. Due to this popularity, understanding misbehavior on WhatsApp is an important issue. The sending of unwanted junk messages by unknown contacts via WhatsApp remains understudied by researchers, in part because of the end-to-end encryption offered by the platform. We address this gap by studying junk messaging on a multilingual dataset of 2.6M messages sent to 5K public WhatsApp groups in India. We characterise both junk content and senders. We find that nearly 1 in 10 messages is unwanted content sent by junk senders, and a number of unique strategies are employed to reflect challenges faced on WhatsApp, e.g., the need to change phone numbers regularly. We finally experiment with on-device classification to automate the detection of junk, whilst respecting end-to-end encryption.

cs.CR↗

arXiv2021

Exploring Content Moderation in the Decentralised Web: The Pleroma Case

Decentralising the Web is a desirable but challenging goal. One particular challenge is achieving decentralised content moderation in the face of various adversaries (e.g. trolls). To overcome this challenge, many Decentralised Web (DW) implementations rely on federation policies. Administrators use these policies to create rules that ban or modify content that matches specific rules. This, however, can have unintended consequences for many users. In this paper, we present the first study of federation policies on the DW, their in-the-wild usage, and their impact on users. We identify how these policies may negatively impact "innocent" users and outline possible solutions to avoid this problem in the future.

cs.CY↗

arXiv2021

360NorVic: 360-Degree Video Classification from Mobile Encrypted Video Traffic

Streaming 360° video demands high bandwidth and low latency, and poses significant challenges to Internet Service Providers (ISPs) and Mobile Network Operators (MNOs). The identification of 360° video traffic can therefore benefits fixed and mobile carriers to optimize their network and provide better Quality of Experience (QoE) to the user. However, end-to-end encryption of network traffic has obstructed identifying those 360° videos from regular videos. As a solution this paper presents 360NorVic, a near-realtime and offline Machine Learning (ML) classification engine to distinguish 360° videos from regular videos when streamed from mobile devices. We collect packet and flow level data for over 800 video traces from YouTube & Facebook accounting for 200 unique videos under varying streaming conditions. Our results show that for near-realtime and offline classification at packet level, average accuracy exceeds 95%, and that for flow level, 360NorVic achieves more than 92% average accuracy. Finally, we pilot our solution in the commercial network of a large MNO showing the feasibility and effectiveness of 360NorVic in production settings.

cs.MM↗

arXiv2020

The Making of 5G: Building an End-to-End 5G-Enabled System

This article documents one of the world's first standards-compliant pre-commercial end-to-end 5th generation (5G) systems. Focus is on a standardized 5G architecture which includes the underlying 3GPP components but also the ETSI Network Function Virtualization (NFV) management and orchestration capabilities. The truly innovative character of 5G enabling fundamental changes to architecture and implementation is discussed, and details of monitoring and orchestration approaches that are deemed instrumental in unlocking the full potential of 5G. Finally, it is important to us to share the lessons learned which we hope are of use to industry and academia alike when building, deploying and testing emerging 5G systems.

cs.NI↗

arXiv2020

Dissecting the Workload of a Major Adult Video Portal

Adult content constitutes a major source of Internet traffic. As with many other platforms, these sites are incentivized to engage users and maintain them on the site. This engagement (e.g., through recommendations) shapes the journeys taken through such sites. Using data from a large content delivery network, we explore session journeys within an adult website. We take two perspectives. We first inspect the corpus available on these platforms. Following this, we investigate the session access patterns. We make a number of observations that could be exploited for optimizing delivery, e.g., that users often skip within video streams.

cs.CY↗

arXiv2019

Challenges in the Decentralised Web: The Mastodon Case

The Decentralised Web (DW) has recently seen a renewed momentum, with a number of DW platforms like Mastodon, Peer-Tube, and Hubzilla gaining increasing traction. These offer alternatives to traditional social networks like Twitter, YouTube, and Facebook, by enabling the operation of web infrastructure and services without centralised ownership or control. Although their services differ greatly, modern DW platforms mostly rely on two key innovations: first, their open source software allows anybody to setup independent servers ("instances") that people can sign-up to and use within a local community; and second, they build on top of federation protocols so that instances can mesh together, in a peer-to-peer fashion, to offer a globally integrated platform. In this paper, we present a measurement-driven exploration of these two innovations, using a popular DW microblogging platform (Mastodon) as a case study. We focus on identifying key challenges that might disrupt continuing efforts to decentralise the web, and empirically highlight a number of properties that are creating natural pressures towards recentralisation. Finally, our measurements shed light on the behaviour of both administrators (i.e., people setting up instances) and regular users who sign-up to the platforms, also discussing a few techniques that may address some of the issues observed.

cs.NI↗

arXiv2018

Facebook (A)Live? Are live social broadcasts really broadcasts?

The era of live-broadcast is back but with two major changes. First, unlike traditional TV broadcasts, content is now streamed over the Internet enabling it to reach a wider audience. Second, due to various user-generated content platforms it has become possible for anyone to get involved, streaming their own content to the world. This emerging trend of going live usually happens via social platforms, where users perform live social broadcasts predominantly from their mobile devices, allowing their friends (and the general public) to engage with the stream in real-time. With the growing popularity of such platforms, the burden on the current Internet infrastructure is therefore expected to multiply. With this in mind, we explore one such prominent platform - Facebook Live. We gather 3TB of data, representing one month of global activity and explore the characteristics of live social broadcast. From this, we derive simple yet effective principles which can decrease the network burden. We then dissect global and hyper-local properties of the video while on-air, by capturing the geography of the broadcasters or the users who produce the video and the viewers or the users who interact with it. Finally, we study the social engagement while the video is live and distinguish the key aspects when the same video goes on-demand. A common theme throughout the paper is that, despite its name, many attributes of Facebook Live deviate from both the concepts of live and broadcast.

cs.SI↗