arXiv subjects

Indranil Gupta

Publications and source records attributed to Indranil Gupta.

28 records · Page 2Linked to original sources

arXiv2020

Home, SafeHome: Smart Home Reliability with Visibility and Atomicity

Smart environments (homes, factories, hospitals, buildings) contain an increasing number of IoT devices, making them complex to manage. Today, in smart homes where users or triggers initiate routines (i.e., a sequence of commands), concurrent routines and device failures can cause incongruent outcomes. We describe SafeHome, a system that provides notions of atomicity and serial equivalence for smart homes. Due to the human-facing nature of smart homes, SafeHome offers a spectrum of {\it visibility models} which trade off between responsiveness vs. incongruence of the smart home state. We implemented SafeHome and performed workload-driven experiments. We find that a weak visibility model, called {\it eventual visibility}, is almost as fast as today's status quo (up to 23\% slower) and yet guarantees serially-equivalent end states.

cs.DC↗

arXiv2019

SLSGD: Secure and Efficient Distributed On-device Machine Learning

We consider distributed on-device learning with limited communication and security requirements. We propose a new robust distributed optimization algorithm with efficient communication and attack tolerance. The proposed algorithm has provable convergence and robustness under non-IID settings. Empirical results show that the proposed algorithm stabilizes the convergence and tolerates data poisoning on a small number of workers.

cs.LG↗

arXiv2019

Zeno: Distributed Stochastic Gradient Descent with Suspicion-based Fault-tolerance

We present Zeno, a technique to make distributed machine learning, particularly Stochastic Gradient Descent (SGD), tolerant to an arbitrary number of faulty workers. Zeno generalizes previous results that assumed a majority of non-faulty nodes; we need assume only one non-faulty worker. Our key idea is to suspect workers that are potentially defective. Since this is likely to lead to false positives, we use a ranking-based preference mechanism. We prove the convergence of SGD for non-convex problems under these scenarios. Experimental results show that Zeno outperforms existing approaches.

cs.LG↗

arXiv2019

Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulation

Recently, new defense techniques have been developed to tolerate Byzantine failures for distributed machine learning. The Byzantine model captures workers that behave arbitrarily, including malicious and compromised workers. In this paper, we break two prevailing Byzantine-tolerant techniques. Specifically we show robust aggregation methods for synchronous SGD -- coordinate-wise median and Krum -- can be broken using new attack strategies based on inner product manipulation. We prove our results theoretically, as well as show empirical validation.

cs.LG↗

arXiv2018

Phocas: dimensional Byzantine-resilient stochastic gradient descent

We propose a novel robust aggregation rule for distributed synchronous Stochastic Gradient Descent~(SGD) under a general Byzantine failure model. The attackers can arbitrarily manipulate the data transferred between the servers and the workers in the parameter server~(PS) architecture. We prove the Byzantine resilience of the proposed aggregation rules. Empirical analysis shows that the proposed techniques outperform current approaches for realistic use cases and Byzantine attack scenarios.

cs.DC↗

arXiv2018

Generalized Byzantine-tolerant SGD

We propose three new robust aggregation rules for distributed synchronous Stochastic Gradient Descent~(SGD) under a general Byzantine failure model. The attackers can arbitrarily manipulate the data transferred between the servers and the workers in the parameter server~(PS) architecture. We prove the Byzantine resilience properties of these aggregation rules. Empirical analysis shows that the proposed techniques outperform current approaches for realistic use cases and Byzantine attack scenarios.

cs.DC↗

arXiv2018

Henge: Intent-driven Multi-Tenant Stream Processing

We present Henge, a system to support intent-based multi-tenancy in modern stream processing applications. Henge supports multi-tenancy as a first-class citizen: everyone inside an organization can now submit their stream processing jobs to a single, shared, consolidated cluster. Additionally, Henge allows each tenant (job) to specify its own intents (i.e., requirements) as a Service Level Objective (SLO) that captures latency and/or throughput. In a multi-tenant cluster, the Henge scheduler adapts continually to meet jobs' SLOs in spite of limited cluster resources, and under dynamic input workloads. SLOs are soft and are based on utility functions. Henge continually tracks SLO satisfaction, and when jobs miss their SLOs, it wisely navigates the state space to perform resource allocations in real time, maximizing total system utility achieved by all jobs in the system. Henge is integrated in Apache Storm and we present experimental results using both production topologies and real datasets.

cs.DC↗

arXiv2017

Inferring Formal Properties of Production Key-Value Stores

Production distributed systems are challenging to formally verify, in particular when they are based on distributed protocols that are not rigorously described or fully understood. In this paper, we derive models and properties for two core distributed protocols used in eventually consistent production key-value stores such as Riak and Cassandra. We propose a novel modeling called certified program models, where complete distributed systems are captured as programs written in traditional systems languages such as concurrent C. Specifically, we model the read-repair and hinted-handoff recovery protocols as concurrent C programs, test them for conformance with real systems, and then verify that they guarantee eventual consistency, modeling precisely the specification as well as the failure assumptions under which the results hold.

cs.DC↗

arXiv2016

Characterizing and Adapting the Consistency-Latency Tradeoff in Distributed Key-value Stores

The CAP theorem is a fundamental result that applies to distributed storage systems. In this paper, we first present and prove two CAP-like impossibility theorems. To state these theorems, we present probabilistic models to characterize the three important elements of the CAP theorem: consistency (C), availability or latency (A), and partition tolerance (P). The theorems show the un-achievable envelope, i.e., which combinations of the parameters of the three models make them impossible to achieve together. Next, we present the design of a class of systems called PCAP that perform close to the envelope described by our theorems. In addition, these systems allow applications running on a single data-center to specify either a latency SLA or a consistency SLA. The PCAP systems automatically adapt, in real-time and under changing network conditions, to meet the SLA while optimizing the other C/A metric. We incorporate PCAP into two popular key-value stores -- Apache Cassandra and Riak. Our experiments with these two deployments, under realistic workloads, reveal that the PCAP system satisfactorily meets SLAs, and performs close to the achievable envelope. We also extend PCAP from a single data-center to multiple geo-distributed data-centers.

cs.DC↗

arXiv2005

Leveraging Social-Network Infrastructure to Improve Peer-to-Peer Overlay Performance: Results from Orkut

Application-level peer-to-peer (P2P) network overlays are an emerging paradigm that facilitates decentralization and flexibility in the scalable deployment of applications such as group communication, content delivery, and data sharing. However the construction of the overlay graph topology optimized for low latency, low link and node stress and lookup performance is still an open problem. We present a design of an overlay constructed on top of a social network and show that it gives a sizable improvement in lookups, average round-trip delay and scalability as opposed to other overlay topologies. We build our overlay on top of the topology of a popular real-world social network namely Orkut. We show Orkuts suitability for our purposes by evaluating the clustering behavior of its graph structure and the socializing pattern of its members.

cs.NI↗