Tag Archives: scientific

On Max-min Fair Allocation for Multi-source Transmission

Geng Li, Yichen Qian, Y. Richard Yang

Abstract

Max-min fair is widely used in network traffic engineering to allocate available resources among different traffic transfers. Recently, as data replication technique developed, increasing systems enforce multi-source transmission to maximize network utilization. However, existing TE approaches fail to deal with multi-source transfers because the optimization becomes a joint problem of bandwidth allocation as well as flow assignment among different sources. In this paper, we present a novel allocation approach for multi-source transfers to achieve global max-min fairness. The joint bandwidth allocation and flow assignment optimization problem poses a major challenge due to nonlinearity and multiple objectives. We cope with this by deriving a novel transformation with simple equivalent canonical linear programming to achieve global optimality efficiently. We conduct data-driven simulations, showing that our approach is more max-min fair than other single-source and multi-source allocation approaches, meanwhile it outperforms others with substantial gains in terms of network throughput and transfer completion time.

Download the full article

On Collaborative Predictive Blacklisting

Luca Melis, Apostolos Pyrgelis, Emiliano De Cristofaro

Abstract

Collaborative predictive blacklisting (CPB) allows to forecast future attack sources based on logs and alerts contributed by multiple organizations. Unfortunately, however, research on CPB has only focused on increasing the number of predicted attacks but has not considered the impact on false positives and false negatives. Moreover, sharing alerts is often hindered by confidentiality, trust, and liability issues, which motivates the need for privacy-preserving approaches to the problem. In this paper, we present a measurement study of state-of-the-art CPB techniques, aiming to shed light on the actual impact of collaboration. To this end, we reproduce and measure two systems: a non privacy-friendly one that uses a trusted coordinating party with access to all alerts [12] and a peer-to-peer one using privacy-preserving data sharing [8]. We show that, while collaboration boosts the number of predicted attacks, it also yields high false positives, ultimately leading to poor accuracy. This motivates us to present a hybrid approach, using a semi-trusted central entity, aiming to increase utility from collaboration while, at the same time, limiting information disclosure and false positives. This leads to a better trade-off of true and false positive rates, while at the same time addressing privacy concerns.

Download the full article

Bootstrapping Privacy Services in Today’s Internet

Taeho Lee, Christos Pappas, Adrian Perrig

Abstract

Internet users today have few solutions to cover a large space of diverse privacy requirements. We introduce the concept of privacy domains, which provide flexibility in expressing users’ privacy requirements. Then, we propose three privacy services that construct meaningful privacy domains and can be offered by ISPs. Furthermore, we illustrate that these services introduce little overhead for communication sessions and that they come with a low deployment barrier for ISPs.

Download the full article

Learning IP Network Representations

Mingda Li, Cristian Lumezanu, Bo Zong, Haifeng Chen

Abstract

We present DIP, a deep learning based framework to learn structural properties of the Internet, such as node clustering or distance between nodes. Existing embedding-based approaches use linear algorithms on a single source of data, such as latency or hop count information, to approximate the position of a node in the Internet. In contrast, DIP computes low-dimensional representations of nodes that preserve structural properties and non-linear relationships across multiple, heterogeneous sources of structural information, such as IP, routing, and distance information. Using a large real-world data set, we show that DIP learns representations that preserve the real-world clustering of the associated nodes and predicts distance between them more than 30% better than a meanbased approach. Furthermore, DIP accurately imputes hop count distance to unknown hosts (i.e., not used in training) given only their IP addresses and routable prefixes. Our framework is extensible to new data sources and applicable to a wide range of problems in network monitoring and security

Download the full article

Refining Network Intents for Self-Driving Networks

Arthur Selle Jacobs, Ricardo José Pfitscher , Ronaldo Alves Ferreira, Lisandro Zambenedetti Granville

Abstract

Recent advances in artificial intelligence (AI) offer an opportunity for the adoption of self-driving networks. However, network operators or home-network users still do not have the right tools to exploit these new advancements in AI, since they have to rely on low-level languages to specify network policies. Intent-based networking (IBN) allows operators to specify high-level policies that dictate how the network should behave without worrying how they are translated into configuration commands in the network devices. However, the existing research proposals for IBN fail to exploit the knowledge and feedback from the network operator to validate or improve the translation of intents. In this paper, we introduce a novel intent-refinement process that uses machine learning and feedback from the operator to translate the operator’s utterances into network configurations. Our refinement process uses a sequence-to-sequence learning model to extract intents from natural language and the feedback from the operator to improve learning. The key insight of our process is an intermediate representation that resembles natural language that is suitable to collect feedback from the operator but is structured enough to facilitate precise translations. Our prototype interacts with a network operator using natural language and translates the operator input to the intermediate representation before translating to SDN rules. Our experimental results show that our process achieves a correlation coefficient squared (i.e., R-squared of 0.99 for a dataset with 5000 entries and the operator feedback significantly improves the accuracy of our model.

Download the full article

Making Content Caching Policies ‘Smart’ using the DeepCache Framework

Arvind Narayanan, Saurabh Verma, Eman Ramadan, Pariya Babaie, Zhi-Li Zhang

Abstract

In this paper, we present DeepCache a novel framework for content caching, which can significantly boost cache performance. Our framework is based on powerful deep recurrent neural network models. It comprises of two main components: i) Object Characteristics Predictor, which builds upon deep LSTM Encoder-Decoder model to predict the future characteristics of an object (such as object popularity) — to the best of our knowledge, we are the first to propose LSTM Encoder-Decoder model for content caching; ii) a caching policy component, which accounts for predicted information of objects to make smart caching decisions. In our thorough experiments, we show that applying DeepCache Framework to existing cache policies, such as LRU and k-LRU, significantly boosts the number of cache hits.

Download the full article

Measuring the Impact of a Successful DDoS Attack on the Customer Behaviour of Managed DNS Service Providers

Abhishta Abhishta, Roland van Rijswijk-Deij
and Lambert J. M. Nieuwenhuis
Abstract

Distributed Denial-of-Service (DDoS) attacks continue to pose a serious threat to the availability of Internet services. The Domain Name System (DNS) is part of the core of the Internet and a crucial factor in the successful delivery of Internet services. Because of the importance of DNS, specialist service providers have sprung up in the market, that provide managed DNS services. One of their key selling points is that they protect DNS for a domain against DDoS attacks. But what if such a service becomes the target of a DDoS attack, and that attack succeeds?

In this paper we analyse two such events, an attack on NS1 in May 2016, and an attack on Dyn in October 2016. We do this by analysing the change in the behaviour of the service’s customers. For our analysis we leverage data from the OpenINTEL active DNS measurement system, which covers large parts of the global DNS over time. Our results show an almost immediate and statistically significant change in the behaviour of domains that use NS1 or Dyn as a DNS service provider. We observe a decline in the number of domains that exclusively use NS1 or Dyn as a managed DNS service provider, and see a shift toward risk spreading by using multiple providers. While a large managed DNS provider may be better equipped to protect against attacks, these two case studies show they are not impervious to them. This calls into question the wisdom of using a single provider for managed DNS. Our results show that spreading risk by using multiple providers is an effective countermeasure, albeit probably at a higher cost.

Download the full article

A Formally Verified NAT Stack

Solal Pirelli, Arseniy Zaostrovnykh, George Candea
Abstract

Prior work proved a stateful NAT network function to be semantically correct, crash-free, and memory safe. Their toolchain verifies the network function code while assuming the underlying kernel-bypass framework, drivers, operating system, and hardware to be correct. We extend the toolchain to verify the kernel-bypass framework and a NIC driver in the context of the NAT. We uncover bugs in both the framework and the driver. Our code is publicly available.

Download the full article

Accelerating Network Measurement in Software

Yang ZhouOmid Alipourfard, Minlan YuTong Yang
Abstract

Network measurement plays an important role for many network functions such as detecting network anomalies and identifying big flows. However, most existing measurement solutions fail to achieve high performance in software as they often incorporate heavy computations and a large number of random memory accesses. We present Agg-Evict, a generic framework for accelerating network measurement in software. Agg-Evict aggregates the incoming packets on the same flows and sends them as a batch, reducing the number of computations and random memory accesses in the subsequent measurement solutions. We perform extensive experiments on top of DPDK with 10G NIC and observe that almost all the tested measurement solutions under Agg-Evict can achieve 14.88 Mpps throughput and see up to 5.7× lower average processing latency per packet.

Download the full article

Looking for Hypergiants in PeeringDB

Timm Böttger, Felix Cuadrado, Steve Uhlig
Abstract

Hypergiants, such as Google or Netflix, are important organisations in the Internet ecosystem, due to their sheer impact in terms of traffic volume exchanged. However, the research community still lacks a sufficiently crisp definition for them, beyond naming specific instances of them. In this paper we analyse PeeringDB data and identify features that differentiate hypergiants from the other organisations. To this end, we first characterise the organisations present in PeeringDB, allowing us to identify discriminating properties of these organisations. We then use these properties to separate the data in two clusters, differentiating hypergiants from other organisations. We conclude this paper by investigating how hypergiants and other organisations exploit the IXP ecosystem to reach the global IPv4 space.

Download the full article