arXiv subjects

Suhas Diggavi

Publications and source records attributed to Suhas Diggavi.

At least 55 records · Page 3Linked to original sources

arXiv2020

Shuffled Model of Federated Learning: Privacy, Communication and Accuracy Trade-offs

We consider a distributed empirical risk minimization (ERM) optimization problem with communication efficiency and privacy requirements, motivated by the federated learning (FL) framework. Unique challenges to the traditional ERM problem in the context of FL include (i) need to provide privacy guarantees on clients' data, (ii) compress the communication between clients and the server, since clients might have low-bandwidth links, (iii) work with a dynamic client population at each round of communication between the server and the clients, as a small fraction of clients are sampled at each round. To address these challenges we develop (optimal) communication-efficient schemes for private mean estimation for several $\ell_p$ spaces, enabling efficient gradient aggregation for each iteration of the optimization solution of the ERM. We also provide lower and upper bounds for mean estimation with privacy and communication constraints for arbitrary $\ell_p$ spaces. To get the overall communication, privacy, and optimization performance operation point, we combine this with privacy amplification opportunities inherent to this setup. Our solution takes advantage of the inherent privacy amplification provided by client sampling and data sampling at each client (through Stochastic Gradient Descent) as well as the recently developed privacy framework using anonymization, which effectively presents to the server responses that are randomly shuffled with respect to the clients. Putting these together, we demonstrate that one can get the same privacy, optimization-performance operating point developed in recent methods that use full-precision communication, but at a much lower communication cost, i.e., effectively getting communication efficiency for "free".

cs.LG↗

arXiv2020

Byzantine-Resilient High-Dimensional Federated Learning

We study stochastic gradient descent (SGD) with local iterations in the presence of malicious/Byzantine clients, motivated by the federated learning. The clients, instead of communicating with the central server in every iteration, maintain their local models, which they update by taking several SGD iterations based on their own datasets and then communicate the net update with the server, thereby achieving communication-efficiency. Furthermore, only a subset of clients communicate with the server, and this subset may be different at different synchronization times. The Byzantine clients may collaborate and send arbitrary vectors to the server to disrupt the learning process. To combat the adversary, we employ an efficient high-dimensional robust mean estimation algorithm from Steinhardt et al.~\cite[ITCS 2018]{Resilience_SCV18} at the server to filter-out corrupt vectors; and to analyze the outlier-filtering procedure, we develop a novel matrix concentration result that may be of independent interest. We provide convergence analyses for strongly-convex and non-convex smooth objectives in the heterogeneous data setting, where different clients may have different local datasets, and we do not make any probabilistic assumptions on data generation. We believe that ours is the first Byzantine-resilient algorithm and analysis with local iterations. We derive our convergence results under minimal assumptions of bounded variance for SGD and bounded gradient dissimilarity (which captures heterogeneity among local datasets). We also extend our results to the case when clients compute full-batch gradients.

stat.ML↗

arXiv2020

Distortion based Light-weight Security for Cyber-Physical Systems

In Cyber-Physical Systems (CPS), inference based on communicated data is of critical significance as it can be used to manipulate or damage the control operations by adversaries. This calls for efficient mechanisms for secure transmission of data since control systems are becoming increasingly distributed over larger geographical areas. Distortion based security, recently proposed as one candidate for secure transmissions in CPS, is not only more appropriate for these applications but also quite frugal in terms of prior requirements on shared keys. In this paper, we propose distortion-based metrics to protect CPS communication and show that it is possible to confuse adversaries with just a few bits of pre-shared keys. In particular, we will show that a linear dynamical system can communicate its state in a manner that prevents an eavesdropper from accurately learning the state.

cs.IT↗

arXiv2020

Coded Caching for Heterogeneous Wireless Networks

This chapter provides an overview of coded caching in the context of heterogeneous wireless networks. We begin by briefly describing the key idea behind coded caching and then discuss in detail the impact of various aspects such as non-uniform content popularity, multiple cache access, and interference.

cs.IT↗

arXiv2020

Algorithms for reconstruction over single and multiple deletion channels

Recent advances in DNA sequencing technology and DNA storage systems have rekindled the interest in deletion channels. Multiple recent works have looked at variants of sequence reconstruction over a single and over multiple deletion channels, a notoriously difficult problem due to its highly combinatorial nature. Although works in theoretical computer science have provided algorithms which guarantee perfect reconstruction with multiple independent observations from the deletion channel, they are only applicable in the large blocklength regime and more restrictively, when the number of observations is also large. Indeed, with only a few observations, perfect reconstruction of the input sequence may not even be possible in most cases. In such situations, maximum likelihood (ML) and maximum aposteriori (MAP) estimates for the deletion channels are natural questions that arise and these have remained open to the best of our knowledge. In this work, we take steps to answer the two aforementioned questions. Specifically: 1. We show that solving for the ML estimate over the single deletion channel (which can be cast as a discrete optimization problem) is equivalent to solving its relaxation, a continuous optimization problem; 2. We exactly compute the symbolwise posterior distributions (under some assumptions on the priors) for both the single as well as multiple deletion channels. As part of our contributions, we also introduce tools to visualize and analyze error events, which we believe could be useful in other related problems concerning deletion channels.

cs.IT↗

arXiv2020

Successive Refinement of Privacy

This work examines a novel question: how much randomness is needed to achieve local differential privacy (LDP)? A motivating scenario is providing {\em multiple levels of privacy} to multiple analysts, either for distribution or for heavy-hitter estimation, using the \emph{same} (randomized) output. We call this setting \emph{successive refinement of privacy}, as it provides hierarchical access to the raw data with different privacy levels. For example, the same randomized output could enable one analyst to reconstruct the input, while another can only estimate the distribution subject to LDP requirements. This extends the classical Shannon (wiretap) security setting to local differential privacy. We provide (order-wise) tight characterizations of privacy-utility-randomness trade-offs in several cases for distribution estimation, including the standard LDP setting under a randomness constraint. We also provide a non-trivial privacy mechanism for multi-level privacy. Furthermore, we show that we cannot reuse random keys over time while preserving privacy of each user.

cs.CR↗

arXiv2020

Byzantine-Resilient SGD in High Dimensions on Heterogeneous Data

We study distributed stochastic gradient descent (SGD) in the master-worker architecture under Byzantine attacks. We consider the heterogeneous data model, where different workers may have different local datasets, and we do not make any probabilistic assumptions on data generation. At the core of our algorithm, we use the polynomial-time outlier-filtering procedure for robust mean estimation proposed by Steinhardt et al. (ITCS 2018) to filter-out corrupt gradients. In order to be able to apply their filtering procedure in our {\em heterogeneous} data setting where workers compute {\em stochastic} gradients, we derive a new matrix concentration result, which may be of independent interest. We provide convergence analyses for smooth strongly-convex and non-convex objectives. We derive our results under the bounded variance assumption on local stochastic gradients and a {\em deterministic} condition on datasets, namely, gradient dissimilarity; and for both these quantities, we provide concrete bounds in the statistical heterogeneous data model. We give a trade-off between the mini-batch size for stochastic gradients and the approximation error. Our algorithm can tolerate up to $\frac{1}{4}$ fraction Byzantine workers. It can find approximate optimal parameters in the strongly-convex setting exponentially fast and reach to an approximate stationary point in the non-convex setting with a linear speed, thus, matching the convergence rates of vanilla SGD in the Byzantine-free setting. We also propose and analyze a Byzantine-resilient SGD algorithm with gradient compression, where workers send $k$ random coordinates of their gradients. Under mild conditions, we show a $\frac{d}{k}$-factor saving in communication bits as well as decoding complexity over our compression-free algorithm without affecting its convergence rate (order-wise) and the approximation error.

stat.ML↗

arXiv2020

SPARQ-SGD: Event-Triggered and Compressed Communication in Decentralized Stochastic Optimization

In this paper, we propose and analyze SPARQ-SGD, which is an event-triggered and compressed algorithm for decentralized training of large-scale machine learning models. Each node can locally compute a condition (event) which triggers a communication where quantized and sparsified local model parameters are sent. In SPARQ-SGD each node takes at least a fixed number ($H$) of local gradient steps and then checks if the model parameters have significantly changed compared to its last update; it communicates further compressed model parameters only when there is a significant change, as specified by a (design) criterion. We prove that the SPARQ-SGD converges as $O(\frac{1}{nT})$ and $O(\frac{1}{\sqrt{nT}})$ in the strongly-convex and non-convex settings, respectively, demonstrating that such aggressive compression, including event-triggered communication, model sparsification and quantization does not affect the overall convergence rate as compared to uncompressed decentralized training; thereby theoretically yielding communication efficiency for "free". We evaluate SPARQ-SGD over real datasets to demonstrate significant amount of savings in communication over the state-of-the-art.

stat.ML↗

arXiv2020

Generalized Degrees of Freedom of Noncoherent Diamond Networks

We study the generalized degrees of freedom (gDoF) of the block-fading noncoherent diamond (parallel relay) wireless network with asymmetric distributions of link strengths, and a coherence time of T symbol duration. We first derive an outer bound for this channel and then derive the optimal signaling structure for this outer bound. Using the optimal signaling structure we solve the outer bound optimization problem in terms of its gDoF. Using insights from our outer bound signaling solution, we devise an achievability strategy based on a novel scheme that we call train-scale quantize-map-forward (TS-QMF). This uses training in the links from the source to the relays, scaling and quantizing at the relays combined with nontraining-based schemes. We show the optimality of this scheme with respect to the outer bound in terms of the gDoF. In noncoherent point-to-point multiple-input-multiple-output (MIMO) channels, where the fading channel is unknown to transmitter and receiver, an important tradeoff between communication and channel learning was revealed by Zheng and Tse, by demonstrating that not all the available antennas might be used, as it is suboptimal to learn all their channel parameters. Our results in this paper for the diamond network demonstrates that in certain regimes the optimal scheme uses a subnetwork, demonstrating a tradeoff between channel learning and communications. In some regimes, it is gDoF optimal to do relay selection, i.e, use a part of the network. In the other regimes, even when it is essential to use the entire network, it is suboptimal to learn the channel states for all the links in the network, i.e, traditional training-based schemes are suboptimal in these regimes.

cs.IT↗

arXiv2019

Password Cracking: The Effect of Hash Function Bias on the Average Guesswork

Modern authentication systems store hashed values of passwords of users using cryptographic hash functions. Therefore, to crack a password an attacker needs to guess a hash function input that is mapped to the hashed value, as opposed to the password itself. We call a hash function that maps the same number of inputs to each bin, as \textbf{unbiased}. However, cryptographic hash functions in use have not been proven to be unbiased (i.e., they may have an unequal number of inputs mapped to different bins). A cryptographic hash function has the property that it is computationally difficult to find an input mapped to a bin. In this work we introduce a structured notion of biased hash functions for which we analyze the average guesswork under certain types of brute force attacks. This work shows that the level of security depends on the set of hashed values of valid users as well as the statistical profile of a hash function, resulting from bias. We examine the average guesswork conditioned on the set of hashed values, and model the statistical profile through the empirical distribution of the number of inputs that are mapped to a bin. In particular, we focus on a class of statistical profiles (capturing the bias) , which we call type-class statistical profiles, that has an empirical distribution related to the probability of the type classes defined in the method of types. For such profiles, we show that the average guesswork is related to basic measures in information theory such as entropy and divergence. We use this to show that the effect of bias on the conditional average guesswork is limited compared to other system parameters such as the number of valid users who store their hashed passwords in the system.

cs.CR↗

arXiv2019

Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computations

Communication bottleneck has been identified as a significant issue in distributed optimization of large-scale learning models. Recently, several approaches to mitigate this problem have been proposed, including different forms of gradient compression or computing local models and mixing them iteratively. In this paper, we propose \emph{Qsparse-local-SGD} algorithm, which combines aggressive sparsification with quantization and local computation along with error compensation, by keeping track of the difference between the true and compressed gradients. We propose both synchronous and asynchronous implementations of \emph{Qsparse-local-SGD}. We analyze convergence for \emph{Qsparse-local-SGD} in the \emph{distributed} setting for smooth non-convex and convex objective functions. We demonstrate that \emph{Qsparse-local-SGD} converges at the same rate as vanilla distributed SGD for many important classes of sparsifiers and quantizers. We use \emph{Qsparse-local-SGD} to train ResNet-50 on ImageNet and show that it results in significant savings over the state-of-the-art, in the number of bits transmitted to reach target accuracy.

stat.ML↗

arXiv2019

On Distributed Quantization for Classification

We consider the problem of distributed feature quantization, where the goal is to enable a pretrained classifier at a central node to carry out its classification on features that are gathered from distributed nodes through communication constrained channels. We propose the design of distributed quantization schemes specifically tailored to the classification task: unlike quantization schemes that help the central node reconstruct the original signal as accurately as possible, our focus is not reconstruction accuracy, but instead correct classification. Our work does not make any apriori distributional assumptions on the data, but instead uses training data for the quantizer design. Our main contributions include: we prove NP-hardness of finding optimal quantizers in the general case; we design an optimal scheme for a special case; we propose quantization algorithms, that leverage discrete neural representations and training data, and can be designed in polynomial-time for any number of features, any number of classes, and arbitrary division of features across the distributed nodes. We find that tailoring the quantizers to the classification task can offer significant savings: as compared to alternatives, we can achieve more than a factor of two reduction in terms of the number of bits communicated, for the same classification accuracy.

cs.LG↗

arXiv2019

Using mm-Waves for Secret Key Establishment

The fact that Millimeter Wave (mmWave) communication needs to be directional is usually perceived as a challenge; in this paper we argue that it enables efficient secret key sharing that are unconditionally secure from passive eavesdroppers, by building on packet erasures. We showcase the potential of our approach in two setups: mmWave-based WiFi networks and vehicle platooning. We show that in the first case, we can establish a few hundred secret bits with minimal changes to standard communication protocol; while in both cases, with the right choice of parameters, we can potentially establish keys in the order of tenths of Mbps. These first results are based on some simplifying assumptions, yet we believe they give incentives to further explore such techniques.

cs.CR↗

arXiv2019

Securing State Estimation Under Sensor and Actuator Attacks: Theory and Design

This paper discusses the problem of estimating the state of a linear time-invariant system when some of its sensors and actuators are compromised by an adversarial agent. In the model considered in this paper, the malicious agent attacks an input (output) by manipulating its value arbitrarily, i.e., we impose no constraints (statistical or otherwise) on how control commands (sensor measurements) are changed by the adversary. In the first part of this paper, we introduce the notion of sparse strong observability and we show that is a necessary and sufficient condition for correctly reconstructing the state despite the considered attacks. In the second half of this work, we propose an estimator to harness the complexity of this intrinsically combinatorial problem, by leveraging satisfiability modulo theory solving. Numerical simulations demonstrate the effectiveness and scalability of our estimator.

math.OC↗

arXiv2019

Differentially Private Consensus-Based Distributed Optimization

Data privacy is an important concern in learning, when datasets contain sensitive information about individuals. This paper considers consensus-based distributed optimization under data privacy constraints. Consensus-based optimization consists of a set of computational nodes arranged in a graph, each having a local objective that depends on their local data, where in every step nodes take a linear combination of their neighbors' messages, as well as taking a new gradient step. Since the algorithm requires exchanging messages that depend on local data, private information gets leaked at every step. Taking $(ε, δ)$-differential privacy (DP) as our criterion, we consider the strategy where the nodes add random noise to their messages before broadcasting it, and show that the method achieves convergence with a bounded mean-squared error, while satisfying $(ε, δ)$-DP. By relaxing the more stringent $ε$-DP requirement in previous work, we strengthen a known convergence result in the literature. We conclude the paper with numerical results demonstrating the effectiveness of our methods for mean estimation.

cs.LG↗

arXiv2019

Privacy-Utility Trade-off of Linear Regression under Random Projections and Additive Noise

Data privacy is an important concern in machine learning, and is fundamentally at odds with the task of training useful learning models, which typically require the acquisition of large amounts of private user data. One possible way of fulfilling the machine learning task while preserving user privacy is to train the model on a transformed, noisy version of the data, which does not reveal the data itself directly to the training procedure. In this work, we analyze the privacy-utility trade-off of two such schemes for the problem of linear regression: additive noise, and random projections. In contrast to previous work, we consider a recently proposed notion of differential privacy that is based on conditional mutual information (MI-DP), which is stronger than the conventional $(ε, δ)$-differential privacy, and use relative objective error as the utility metric. We find that projecting the data to a lower-dimensional subspace before adding noise attains a better trade-off in general. We also make a connection between privacy problem and (non-coherent) SIMO, which has been extensively studied in wireless communication, and use tools from there for the analysis. We present numerical results demonstrating the performance of the schemes.

cs.LG↗

arXiv2018

Distorting an Adversary's View in Cyber-Physical Systems

In Cyber-Physical Systems (CPSs), inference based on communicated data is of critical significance as it can be used to manipulate or damage the control operations by adversaries. This calls for efficient mechanisms for secure transmission of data since control systems are becoming increasingly distributed over larger geographical areas. Distortion based security, recently proposed as one candidate for CPSs security, is not only more appropriate for these applications but also quite frugal in terms of prior requirements on shared keys. In this paper, we propose distortion-based metrics to protect CPSs communication and show that it is possible to confuse adversaries with just a few bits of pre-shared keys.

cs.IT↗

arXiv2018

Implementation and Analysis of Stable PUFs Using Gate Oxide Breakdown

We implement and analyze highly stable PUFs using two random gate oxide breakdown mechanisms: plasma induced breakdown and voltage stressed breakdown. These gate oxide breakdown PUFs can be easily implemented in commercial silicon processes, and they are highly stable. We fabricated bit generation units for the stable PUFs on 99 testchips with 65nm CMOS bulk technology. Measurement results show that the plasma induced breakdown can generate complete stable responses. For the voltage stressed breakdown, the responses are with 0.12\% error probability at a worst case corner, which can be effectively accommodated by taking the majority vote from multiple measurements. Both PUFs show significant area reduction compared to SRAM PUF. We compare methods for evaluating the security level of PUFs such as min-entropy, mutual information and guesswork as well as inter- and intra-FHD, and the popular NIST test suite. We show that guesswork can be viewed as a generalization of min-entropy and mutual information. In addition, we analyze our testchip data and show through various statistical distance measures that the bits are independent. Finally, we propose guesswork as a new statistical measure for the level of statistical independence that also has an operational meaning in terms of security.

cs.CR↗