arXiv subjects

Michael Schapira

Publications and source records attributed to Michael Schapira.

At least 19 recordsLinked to original sources

arXiv2026

A Backward-Compatible Protocol Upgrade for HotNets

This document outlines the changes adopted for ACM HotNets 2026, spanning its scope, review process, and program structure. Rather than isolated adjustments, these changes form a coherent effort to clarify and extend HotNets' role as a venue for agenda-setting research, community discussion, and experimentation with how the networking community evaluates, disseminates, and discusses research. In particular, HotNets 2026 broadens its scope to include perspective and community-facing contributions, introduces distinct evaluation criteria for technical and perspective papers, adopts a more collaborative and discussion-oriented review process, rethinks how accepted work is presented and discussed at the workshop, and explores responsible uses of generative AI (GenAI) in reviewing and research dissemination. We believe these changes will help HotNets continue to serve as a home for ambitious, unconventional, and thought-provoking ideas, while also positioning it as a venue for experimenting with new approaches and formats that larger conferences, e.g., SIGCOMM or NSDI, might later adopt. We use this document to solicit feedback from the community, both on these changes and on how HotNets can best serve the networking community in the future. We plan to collect feedback during and after the event and to prepare a follow-up report summarizing the community's reactions and lessons learned.

cs.NI↗

arXiv2026

AdvNet: Revealing Performance Issues in Network Protocols by Generating Adversarial Environments

Infrastructure protocols like Congestion Control (CC) seek to provide reliable performance across a wide range of Internet environments. Currently, protocol designers assess performance through hand-designed test cases or data sets captured from real environments. However, such approaches may inadvertently overlook critical facets of the algorithm's behavior when they encounter an unanticipated environment or workload. We seek to understand the unanticipated with AdvNet, a system that automatically generates adversarial network environments that cause a target protocol implementation to perform poorly. AdvNet employs machine learning-based optimization to generate environments, and incorporates a robust noise-handling mechanism to mitigate the variability inherent in real-world protocol performance. Although our approach is more general, this paper focuses specifically on transport protocols and their CC implementations. We showcase AdvNet's capability to create adversarial scenarios for 27 kernel-space implementations of both single-path and multi-path CC protocols, for several use cases with different performance goals. AdvNet identifies problematic network conditions that expose previously unnoticed Linux kernel bugs and uncovers hidden limitations in CC implementations, and provides insights about robustness. These results suggest that automated adversarial testing can be a valuable tool in protocol development, and that robustness is a useful new dimension for benchmarking CC protocols.

cs.NI↗

arXiv2025

Unleashing Automated Congestion Control Customization in the Wild

Congestion control (CC) crucially impacts user experience across Internet services like streaming, gaming, AR/VR, and connected cars. Traditionally, CC algorithm design seeks universal control rules that yield high performance across diverse application domains and networks. However, varying service needs and network conditions challenge this approach. We share operational experience with a system that automatically customizes congestion control logic to service needs and network conditions. We discuss design, deployment challenges, and solutions, highlighting performance benefits through case studies in streaming, gaming, connected cars, and more. Our system leverages PCC Vivace, an online-learning based congestion control protocol developed by researchers. Hence, along with insights from customizing congestion control, we also discuss lessons learned and modifications made to adapt PCC Vivace for real-world deployment.

cs.NI↗

arXiv2024

Verifying the Generalization of Deep Learning to Out-of-Distribution Domains

Deep neural networks (DNNs) play a crucial role in the field of machine learning, demonstrating state-of-the-art performance across various application domains. However, despite their success, DNN-based models may occasionally exhibit challenges with generalization, i.e., may fail to handle inputs that were not encountered during training. This limitation is a significant challenge when it comes to deploying deep learning for safety-critical tasks, as well as in real-world settings characterized by substantial variability. We introduce a novel approach for harnessing DNN verification technology to identify DNN-driven decision rules that exhibit robust generalization to previously unencountered input domains. Our method assesses generalization within an input domain by measuring the level of agreement between independently trained deep neural networks for inputs in this domain. We also efficiently realize our approach by using off-the-shelf DNN verification engines, and extensively evaluate it on both supervised and unsupervised DNN benchmarks, including a deep reinforcement learning (DRL) system for Internet congestion control -- demonstrating the applicability of our approach for real-world settings. Moreover, our research introduces a fresh objective for formal verification, offering the prospect of mitigating the challenges linked to deploying DNN-driven systems in real-world scenarios.

cs.LG↗

arXiv2024

The Observer Effect in Computer Networks

Network measurement involves an inherent tradeoff between accuracy and overhead; higher accuracy typically comes at the expense of greater measurement overhead (measurement frequency, number of probe packets, etc.). Capturing the "right" balance between these two desiderata - high accuracy and low overhead - is a key challenge. However, the manner in which accuracy and overhead are traded off is specific to the measurement method, rendering apples-to-apples comparisons difficult. To address this, we put forth a novel analytical framework for quantifying the accuracy-overhead tradeoff for network measurements. Our framework, inspired by the observer effect in modern physics, introduces the notion of a network observer factor, which formally captures the relation between measurement accuracy and overhead. Using our "network observer framework", measurement methods for the same task can be characterized in terms of their network observer factors, allowing for apples-to-apples comparisons. We illustrate the usefulness of our approach by showing how it can be applied to various application domains and validate its conclusions through experimental evaluation.

cs.NI↗

arXiv2023

Verifying Generalization in Deep Learning

Deep neural networks (DNNs) are the workhorses of deep learning, which constitutes the state of the art in numerous application domains. However, DNN-based decision rules are notoriously prone to poor generalization, i.e., may prove inadequate on inputs not encountered during training. This limitation poses a significant obstacle to employing deep learning for mission-critical tasks, and also in real-world environments that exhibit high variability. We propose a novel, verification-driven methodology for identifying DNN-based decision rules that generalize well to new input domains. Our approach quantifies generalization to an input domain by the extent to which decisions reached by independently trained DNNs are in agreement for inputs in this domain. We show how, by harnessing the power of DNN verification, our approach can be efficiently and effectively realized. We evaluate our verification-based approach on three deep reinforcement learning (DRL) benchmarks, including a system for Internet congestion control. Our results establish the usefulness of our approach. More broadly, our work puts forth a novel objective for formal verification, with the potential for mitigating the risks associated with deploying DNN-based systems in the wild.

cs.LG↗

arXiv2023

A Deep Learning Perspective on Network Routing

Routing is, arguably, the most fundamental task in computer networking, and the most extensively studied one. A key challenge for routing in real-world environments is the need to contend with uncertainty about future traffic demands. We present a new approach to routing under demand uncertainty: tackling this challenge as stochastic optimization, and employing deep learning to learn complex patterns in traffic demands. We show that our method provably converges to the global optimum in well-studied theoretical models of multicommodity flow. We exemplify the practical usefulness of our approach by zooming in on the real-world challenge of traffic engineering (TE) on wide-area networks (WANs). Our extensive empirical evaluation on real-world traffic and network topologies establishes that our approach's TE quality almost matches that of an (infeasible) omniscient oracle, outperforming previously proposed approaches, and also substantially lowers runtimes.

cs.NI↗

arXiv2022

Verification-Aided Deep Ensemble Selection

Deep neural networks (DNNs) have become the technology of choice for realizing a variety of complex tasks. However, as highlighted by many recent studies, even an imperceptible perturbation to a correctly classified input can lead to misclassification by a DNN. This renders DNNs vulnerable to strategic input manipulations by attackers, and also oversensitive to environmental noise. To mitigate this phenomenon, practitioners apply joint classification by an *ensemble* of DNNs. By aggregating the classification outputs of different individual DNNs for the same input, ensemble-based classification reduces the risk of misclassifications due to the specific realization of the stochastic training process of any single DNN. However, the effectiveness of a DNN ensemble is highly dependent on its members *not simultaneously erring* on many different inputs. In this case study, we harness recent advances in DNN verification to devise a methodology for identifying ensemble compositions that are less prone to simultaneous errors, even when the input is adversarially perturbed -- resulting in more robustly-accurate ensemble-based classification. Our proposed framework uses a DNN verifier as a backend, and includes heuristics that help reduce the high complexity of directly verifying ensembles. More broadly, our work puts forth a novel universal objective for formal verification that can potentially improve the robustness of real-world, deep-learning-based systems across a variety of application domains.

cs.LG↗

arXiv2021

Towards Scalable Verification of Deep Reinforcement Learning

Deep neural networks (DNNs) have gained significant popularity in recent years, becoming the state of the art in a variety of domains. In particular, deep reinforcement learning (DRL) has recently been employed to train DNNs that realize control policies for various types of real-world systems. In this work, we present the whiRL 2.0 tool, which implements a new approach for verifying complex properties of interest for DRL systems. To demonstrate the benefits of whiRL 2.0, we apply it to case studies from the communication networks domain that have recently been used to motivate formal verification of DRL systems, and which exhibit characteristics that are conducive for scalable verification. We propose techniques for performing k-induction and semi-automated invariant inference on such systems, and leverage these techniques for proving safety and liveness properties that were previously impossible to verify due to the scalability barriers of prior approaches. Furthermore, we show how our proposed techniques provide insights into the inner workings and the generalizability of DRL systems. whiRL 2.0 is publicly available online.

cs.LG↗

arXiv2020

Online Safety Assurance for Deep Reinforcement Learning

Recently, deep learning has been successfully applied to a variety of networking problems. A fundamental challenge is that when the operational environment for a learning-augmented system differs from its training environment, such systems often make badly informed decisions, leading to bad performance. We argue that safely deploying learning-driven systems requires being able to determine, in real time, whether system behavior is coherent, for the purpose of defaulting to a reasonable heuristic when this is not so. We term this the online safety assurance problem (OSAP). We present three approaches to quantifying decision uncertainty that differ in terms of the signal used to infer uncertainty. We illustrate the usefulness of online safety assurance in the context of the proposed deep reinforcement learning (RL) approach to video streaming. While deep RL for video streaming bests other approaches when the operational and training environments match, it is dominated by simple heuristics when the two differ. Our preliminary findings suggest that transitioning to a default policy when decision uncertainty is detected is key to enjoying the performance benefits afforded by leveraging ML without compromising on safety.

cs.LG↗

arXiv2019

Internet Congestion Control via Deep Reinforcement Learning

We present and investigate a novel and timely application domain for deep reinforcement learning (RL): Internet congestion control. Congestion control is the core networking task of modulating traffic sources' data-transmission rates to efficiently utilize network capacity, and is the subject of extensive attention in light of the advent of Internet services such as live video, virtual reality, Internet-of-Things, and more. We show that casting congestion control as RL enables training deep network policies that capture intricate patterns in data traffic and network conditions, and leverage this to outperform the state-of-the-art. We also highlight significant challenges facing real-world adoption of RL-based congestion control, including fairness, safety, and generalization, which are not trivial to address within conventional RL formalism. To facilitate further research and reproducibility of our results, we present a test suite for RL-guided congestion control based on the OpenAI Gym interface.

cs.NI↗

arXiv2018

Pied Piper: Rethinking Internet Data Delivery

We contend that, analogously to the transition from resource-limited on-prem computing to resource-abundant cloud computing, Internet data delivery should also be adapted to a reality in which the cloud offers a virtually unlimited resource, i.e., network capacity, and virtualization enables delegating local tasks, such as routing and congestion control, to the cloud. This necessitates rethinking the traditional roles of inter- and intra-domain routing and conventional end-to-end congestion control. We introduce Optimized Cloudified Delivery (OCD), a holistic approach for optimizing joint Internet/cloud data delivery, and evaluate OCD through hundreds of thousands of file downloads from multiple locations. We start by examining an OCD baseline approach: traffic from a source A to a destination B successively passes through two cloud virtual machines operating as relays - nearest to A and B; and the two cloud relays employ TCP split. We show that even this naive strategy can outperform recently proposed improved end-to-end congestion control paradigms (BBR and PCC) by an order of magnitude. Next, we present a protocol-free, ideal pipe model of data transmission, and identify where today's Internet data delivery mechanisms diverge from this model. We then design and implement OCD Pied Piper. Pied Piper leverages various techniques, including novel kernel-based transport-layer accelerations, to improve the Internet-Cloud interface so as to approximately match the ideal network pipe model.

cs.NI↗

arXiv2017

Oblivious Routing via Random Walks

We present novel oblivious routing algorithms for both splittable and unsplittable multicommodity flow. Our algorithm for minimizing congestion for \emph{unsplittable} multicommodity flow is the first oblivious routing algorithm for this setting. As an intermediate step towards this algorithm, we present a novel generalization of Valiant's classical load balancing scheme for packet-switched networks to arbitrary graphs, which is of independent interest. Our algorithm for minimizing congestion for \emph{splittable} multicommodity flow improves upon the state-of-the-art, in terms of both running time and performance, for graphs that exhibit good expansion guarantees. Our algorithms rely on diffusing traffic via iterative applications of the random walk operator. Consequently, the performance guarantees of our algorithms are derived from the convergence of the random walk operator to the stationary distribution and are expressed in terms of the spectral gap of the graph (which dominates the mixing time).

cs.DS↗

arXiv2017

Large Fixed-Diameter Graphs are Good Expanders

We revisit the classical question of the relationship between the diameter of a graph and its expansion properties. One direction is well understood: expander graphs exhibit essentially the lowest possible diameter. We focus on the reverse direction, showing that "sufficiently large" graphs of fixed diameter and degree must be "good" expanders. We prove this statement for various definitions of "sufficiently large" (multiplicative/additive factor from the largest possible size), for different forms of expansion (edge, vertex, and spectral expansion), and for both directed and undirected graphs. A recurring theme is that the lower the diameter of the graph and (more importantly) the larger its size, the better the expansion guarantees. Aside from inherent theoretical interest, our motivation stems from the domain of network design. Both low-diameter networks and expanders are prominent approaches to designing high-performance networks in parallel computing, HPC, datacenter networking, and beyond. Our results establish that these two approaches are, in fact, inextricably intertwined. We leave the reader with many intriguing questions for future research.

math.CO↗

arXiv2017

A Machine Learning Approach to Routing

Can ideas and techniques from machine learning be leveraged to automatically generate "good" routing configurations? We investigate the power of data-driven routing protocols. Our results suggest that applying ideas and techniques from deep reinforcement learning to this context yields high performance, motivating further research along these lines.

cs.NI↗

arXiv2017

Dynamics at the Boundary of Game Theory and Distributed Computing

We use ideas from distributed computing and game theory to study dynamic and decentralized environments in which computational nodes, or decision makers, interact strategically and with limited information. In such environments, which arise in many real-world settings, the participants act as both economic and computational entities. We exhibit a general non-convergence result for a broad class of dynamics in asynchronous settings. We consider implications of our result across a wide variety of interesting and timely applications: game dynamics, circuit design, social networks, Internet routing, and congestion control. We also study the computational and communication complexity of testing the convergence of asynchronous dynamics. Our work opens a new avenue for research at the intersection of distributed computing and game theory.

cs.GT↗

arXiv2017

Setting Lower Bounds on Truthfulness

We present and discuss general techniques for proving inapproximability results for truthful mechanisms. We make use of these techniques to prove lower bounds on the approximability of several non-utilitarian multi-parameter problems. In particular, we demonstrate the strength of our techniques by exhibiting a lower bound of $2-\frac{1}{m}$ for the scheduling problem with unrelated machines (formulated as a mechanism design problem in the seminal paper of Nisan and Ronen on Algorithmic Mechanism Design). Our lower bound applies to truthful randomized mechanisms (disregarding any computational assumptions on the running time of these mechanisms). Moreover, it holds even for the weaker notion of truthfulness for randomized mechanisms -- i.e., truthfulness in expectation. This lower bound nearly matches the known $\frac{7}{4}$ (randomized) truthful upper bound for the case of two machines (a non-truthful FPTAS exists). No lower bound for truthful randomized mechanisms in multi-parameter settings was previously known. We show an application of our techniques to the workload-minimization problem in networks. We prove our lower bounds for this problem in the inter-domain routing setting presented by Feigenbaum, Papadimitriou, Sami, and Shenker. Finally, we discuss several notions of non-utilitarian "fairness" (Max-Min fairness, Min-Max fairness, and envy minimization). We show how our techniques can be used to prove lower bounds for these notions.

cs.GT↗

arXiv2016

Stateless Computation

We present and explore a model of stateless and self-stabilizing distributed computation, inspired by real-world applications such as routing on today's Internet. Processors in our model do not have an internal state, but rather interact by repeatedly mapping incoming messages ("labels") to outgoing messages and output values. While seemingly too restrictive to be of interest, stateless computation encompasses both classical game-theoretic notions of strategic interaction and a broad range of practical applications (e.g., Internet protocols, circuits, diffusion of technologies in social networks). We embark on a holistic exploration of stateless computation. We tackle two important questions: (1) Under what conditions is self-stabilization, i.e., guaranteed "convergence" to a "legitimate" global configuration, achievable for stateless computation? and (2) What is the computational power of stateless computation? Our results for self-stabilization include a general necessary condition for self-stabilization and hardness results for verifying that a stateless protocol is self-stabilizing. Our main results for the power of stateless computation show that labels of logarithmic length in the number of processors yield substantial computational power even on ring topologies. We present a separation between unidirectional and bidirectional rings (L/poly vs. P/poly), reflecting the sequential nature of computation on a unidirectional ring, as opposed to the parallelism afforded by the bidirectional ring. We leave the reader with many exciting directions for future research.

cs.DC↗