arXiv subjects

Kevin S. Chan

Publications and source records attributed to Kevin S. Chan.

16 recordsLinked to original sources

arXiv2026

Resource-Aware Intrusion Detection in Infrastructure Networks: A Game-Theoretic Approach

Infrastructure networks increasingly rely on distributed sensing to detect intrusions before attackers reach valuable assets. Yet sensing devices, communication resources, and edge server capacity are limited, while intelligent attackers can adapt their routes to the deployed defense. Motivated by integrated sensing and communication (ISAC), we study how sensing and processing resources should be allocated under strategic interaction between a defender and an attacker. We formulate their interaction as a graph security game in which the defender deploys sensing actions under resource and false alarm constraints, while the attacker selects routes to valuable targets. We consider simultaneous play and settings in which the attacker observes either a pure defender configuration or a mixed defender strategy. Our analysis characterizes the existence, structure, and computational complexity of the Nash and Stackelberg equilibria, showing how the attacker's observation of the defense affects equilibrium behavior and when optimal strategies become difficult to compute. We develop algorithms that construct effective pure configurations and refine restricted games for mixed Nash and mixed Stackelberg play. On enumerable instances, their solutions have small mean normalized differences from fully enumerated references; the methods also apply when exhaustive strategy enumeration is impractical. We also identify conditions under which Nash and mixed Stackelberg payoffs are ordered or coincide.

cs.GT↗

arXiv2025

The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape

Deep learning has shown incredible potential across a wide array of tasks, and accompanied by this growth has been an insatiable appetite for data. However, a large amount of data needed for enabling deep learning is stored on personal devices, and recent concerns on privacy have further highlighted challenges for accessing such data. As a result, federated learning (FL) has emerged as an important privacy-preserving technology that enables collaborative training of machine learning models without the need to send the raw, potentially sensitive, data to a central server. However, the fundamental premise that sending model updates to a server is privacy-preserving only holds if the updates cannot be "reverse engineered" to infer information about the private training data. It has been shown under a wide variety of settings that this privacy premise does not hold. In this survey paper, we provide a comprehensive literature review of the different privacy attacks and defense methods in FL. We identify the current limitations of these attacks and highlight the settings in which the privacy of an FL client can be broken. We further dissect some of the successful industry applications of FL and draw lessons for future successful adoption. We survey the emerging landscape of privacy regulation for FL and conclude with future directions for taking FL toward the cherished goal of generating accurate models while preserving the privacy of the data from its participants.

cs.CR↗

arXiv2024

Using Diffusion Models as Generative Replay in Continual Federated Learning -- What will Happen?

Federated learning (FL) has become a cornerstone in decentralized learning, where, in many scenarios, the incoming data distribution will change dynamically over time, introducing continuous learning (CL) problems. This continual federated learning (CFL) task presents unique challenges, particularly regarding catastrophic forgetting and non-IID input data. Existing solutions include using a replay buffer to store historical data or leveraging generative adversarial networks. Nevertheless, motivated by recent advancements in the diffusion model for generative tasks, this paper introduces DCFL, a novel framework tailored to address the challenges of CFL in dynamic distributed learning environments. Our approach harnesses the power of the conditional diffusion model to generate synthetic historical data at each local device during communication, effectively mitigating latent shifts in dynamic data distribution inputs. We provide the convergence bound for the proposed CFL framework and demonstrate its promising performance across multiple datasets, showcasing its effectiveness in tackling the complexities of CFL tasks.

cs.LG↗

arXiv2022

Federated Learning with Flexible Control

Federated learning (FL) enables distributed model training from local data collected by users. In distributed systems with constrained resources and potentially high dynamics, e.g., mobile edge networks, the efficiency of FL is an important problem. Existing works have separately considered different configurations to make FL more efficient, such as infrequent transmission of model updates, client subsampling, and compression of update vectors. However, an important open problem is how to jointly apply and tune these control knobs in a single FL algorithm, to achieve the best performance by allowing a high degree of freedom in control decisions. In this paper, we address this problem and propose FlexFL - an FL algorithm with multiple options that can be adjusted flexibly. Our FlexFL algorithm allows both arbitrary rates of local computation at clients and arbitrary amounts of communication between clients and the server, making both the computation and communication resource consumption adjustable. We prove a convergence upper bound of this algorithm. Based on this result, we further propose a stochastic optimization formulation and algorithm to determine the control decisions that (approximately) minimize the convergence bound, while conforming to constraints related to resource consumption. The advantage of our approach is also verified using experiments.

cs.LG↗

arXiv2022

Joint Coreset Construction and Quantization for Distributed Machine Learning

Coresets are small, weighted summaries of larger datasets, aiming at providing provable error bounds for machine learning (ML) tasks while significantly reducing the communication and computation costs. To achieve a better trade-off between ML error bounds and costs, we propose the first framework to incorporate quantization techniques into the process of coreset construction. Specifically, we theoretically analyze the ML error bounds caused by a combination of coreset construction and quantization. Based on that, we formulate an optimization problem to minimize the ML error under a fixed budget of communication cost. To improve the scalability for large datasets, we identify two proxies of the original objective function, for which efficient algorithms are developed. For the case of data on multiple nodes, we further design a novel algorithm to allocate the communication budget to the nodes while minimizing the overall ML error. Through extensive experiments on multiple real-world datasets, we demonstrate the effectiveness and efficiency of our proposed algorithms for a variety of ML tasks. In particular, our algorithms have achieved more than 90% data reduction with less than 10% degradation in ML performance in most cases.

cs.LG↗

arXiv2022

Communication-efficient k-Means for Edge-based Machine Learning

We consider the problem of computing the k-means centers for a large high-dimensional dataset in the context of edge-based machine learning, where data sources offload machine learning computation to nearby edge servers. k-Means computation is fundamental to many data analytics, and the capability of computing provably accurate k-means centers by leveraging the computation power of the edge servers, at a low communication and computation cost to the data sources, will greatly improve the performance of these analytics. We propose to let the data sources send small summaries, generated by joint dimensionality reduction (DR), cardinality reduction (CR), and quantization (QT), to support approximate k-means computation at reduced complexity and communication cost. By analyzing the complexity, the communication cost, and the approximation error of k-means algorithms based on carefully designed composition of DR/CR/QT methods, we show that: (i) it is possible to compute near-optimal k-means centers at a near-linear complexity and a constant or logarithmic communication cost, (ii) the order of applying DR and CR significantly affects the complexity and the communication cost, and (iii) combining DR/CR methods with a properly configured quantizer can further reduce the communication cost without compromising the other performance metrics. Our theoretical analysis has been validated through experiments based on real datasets.

cs.LG↗

arXiv2020

Resource Allocation in One-dimensional Distributed Service Networks with Applications

We consider assignment policies that allocate resources to users, where both resources and users are located on a one-dimensional line. First, we consider unidirectional assignment policies that allocate resources only to users located to their left. We propose the Move to Right (MTR) policy, which scans from left to right assigning nearest rightmost available resource to a user, and contrast it to the Unidirectional Gale-Shapley (UGS) matching policy. While both policies among all unidirectional policies, minimize the expected distance traveled by a request (request distance), MTR is fairer. Moreover, we show that when user and resource locations are modeled by statistical point processes, and resources are allowed to satisfy more than one user, the spatial system under unidirectional policies can be mapped into bulk service queueing systems, thus allowing the application of many queueing theory results that yield closed form expressions. As we consider a case where different resources can satisfy different numbers of users, we also generate new results for bulk service queues. We also consider bidirectional policies where there are no directional restrictions on resource allocation and develop an algorithm for computing the optimal assignment which is more efficient than known algorithms in the literature when there are more resources than users. Numerical evaluation of performance of unidirectional and bidirectional allocation schemes yields design guidelines beneficial for resource placement. \np{Finally, we present a heuristic algorithm, which leverages the optimal dynamic programming scheme for one-dimensional inputs to obtain approximate solutions to the optimal assignment problem for the two-dimensional scenario and empirically yields request distances within a constant factor of the optimal solution.

cs.PF↗

arXiv2020

You Do (Not) Belong Here: Detecting DPI Evasion Attacks with Context Learning

As Deep Packet Inspection (DPI) middleboxes become increasingly popular, a spectrum of adversarial attacks have emerged with the goal of evading such middleboxes. Many of these attacks exploit discrepancies between the middlebox network protocol implementations, and the more rigorous/complete versions implemented at end hosts. These evasion attacks largely involve subtle manipulations of packets to cause different behaviours at DPI and end hosts, to cloak malicious network traffic that is otherwise detectable. With recent automated discovery, it has become prohibitively challenging to manually curate rules for detecting these manipulations. In this work, we propose CLAP, the first fully-automated, unsupervised ML solution to accurately detect and localize DPI evasion attacks. By learning what we call the packet context, which essentially captures inter-relationships across both (1) different packets in a connection; and (2) different header fields within each packet, from benign traffic traces only, CLAP can detect and pinpoint packets that violate the benign packet contexts (which are the ones that are specially crafted for evasion purposes). Our evaluations with 73 state-of-the-art DPI evasion attacks show that CLAP achieves an Area Under the Receiver Operating Characteristic Curve (AUC-ROC) of 0.963, an Equal Error Rate (EER) of only 0.061 in detection, and an accuracy of 94.6% in localization. These results suggest that CLAP can be a promising tool for thwarting DPI evasion attacks.

cs.CR↗

arXiv2020

Sharing Models or Coresets: A Study based on Membership Inference Attack

Distributed machine learning generally aims at training a global model based on distributed data without collecting all the data to a centralized location, where two different approaches have been proposed: collecting and aggregating local models (federated learning) and collecting and training over representative data summaries (coreset). While each approach preserves data privacy to some extent thanks to not sharing the raw data, the exact extent of protection is unclear under sophisticated attacks that try to infer the raw data from the shared information. We present the first comparison between the two approaches in terms of target model accuracy, communication cost, and data privacy, where the last is measured by the accuracy of a state-of-the-art attack strategy called the membership inference attack. Our experiments quantify the accuracy-privacy-cost tradeoff of each approach, and reveal a nontrivial comparison that can be used to guide the design of model training processes.

cs.LG↗

arXiv2020

Learning and Planning in the Feature Deception Problem

Today's high-stakes adversarial interactions feature attackers who constantly breach the ever-improving security measures. Deception mitigates the defender's loss by misleading the attacker to make suboptimal decisions. In order to formally reason about deception, we introduce the feature deception problem (FDP), a domain-independent model and present a learning and planning framework for finding the optimal deception strategy, taking into account the adversary's preferences which are initially unknown to the defender. We make the following contributions. (1) We show that we can uniformly learn the adversary's preferences using data from a modest number of deception strategies. (2) We propose an approximation algorithm for finding the optimal deception strategy given the learned preferences and show that the problem is NP-hard. (3) We perform extensive experiments to validate our methods and results. In addition, we provide a case study of the credit bureau network to illustrate how FDP implements deception on a real-world problem.

cs.AI↗

arXiv2020

Node Immunization with Non-backtracking Eigenvalues

The non-backtracking matrix and its eigenvalues have many applications in network science and graph mining, such as node and edge centrality, community detection, length spectrum theory, graph distance, and epidemic and percolation thresholds. Moreover, in network epidemiology, the reciprocal of the largest eigenvalue of the non-backtracking matrix is a good approximation for the epidemic threshold of certain network dynamics. In this work, we develop techniques that identify which nodes have the largest impact on the leading non-backtracking eigenvalue. We do so by studying the behavior of the spectrum of the non-backtracking matrix after a node is removed from the graph. From this analysis we derive two new centrality measures: X-degree and X-non-backtracking centrality. We perform extensive experimentation with targeted immunization strategies derived from these two centrality measures. Our spectral analysis and centrality measures can be broadly applied, and will be of interest to both theorists and practitioners alike.

cs.SI↗

arXiv2020

Resource Allocation in One-dimensional Distributed Service Networks

We consider assignment policies that allocate resources to users, where both resources and users are located on a one-dimensional line. First, we consider unidirectional assignment policies that allocate resources only to users located to their left. We propose the Move to Right (MTR) policy, which scans from left to right assigning nearest rightmost available resource to a user, and contrast it to the Unidirectional Gale-Shapley (UGS) matching policy. While both these policies are optimal among all unidirectional policies, we show that they are equivalent with respect to the expected distance traveled by a request (request distance), although MTR is fairer. Moreover, we show that when user and resource locations are modeled by statistical point processes, and resources are allowed to satisfy more than one user, the spatial system under unidirectional policies can be mapped into bulk service queuing systems, thus allowing the application of a plethora of queuing theory results that yield closed form expressions. As we consider a case where different resources can satisfy different numbers of users, we also generate new results for bulk service queues. We also consider bidirectional policies where there are no directional restrictions on resource allocation and develop an algorithm for computing the optimal assignment which is more efficient than known algorithms in the literature when there are more resources than users. Finally, numerical evaluation of performance of unidirectional and bidirectional allocation schemes yields design guidelines beneficial for resource placement.

cs.PF↗

arXiv2020

A4 : Evading Learning-based Adblockers

Efforts by online ad publishers to circumvent traditional ad blockers towards regaining fiduciary benefits, have been demonstrably successful. As a result, there have recently emerged a set of adblockers that apply machine learning instead of manually curated rules and have been shown to be more robust in blocking ads on websites including social media sites such as Facebook. Among these, AdGraph is arguably the state-of-the-art learning-based adblocker. In this paper, we develop A4, a tool that intelligently crafts adversarial samples of ads to evade AdGraph. Unlike the popular research on adversarial samples against images or videos that are considered less- to un-restricted, the samples that A4 generates preserve application semantics of the web page, or are actionable. Through several experiments we show that A4 can bypass AdGraph about 60% of the time, which surpasses the state-of-the-art attack by a significant margin of 84.3%; in addition, changes to the visual layout of the web page due to these perturbations are imperceptible. We envision the algorithmic framework proposed in A4 is also promising in improving adversarial attacks against other learning-based web applications with similar requirements.

cs.CR↗

arXiv2019

Polarization and Fluctuations in Signed Social Networks

Much recent research on social networks has focused on the modeling and analysis of how opinions evolve as a function of interpersonal relationships. It is also of great interest to model and understand the implications of friendly and antagonistic relationships. In this paper, we propose a new, simple and intuitive model that incorporates the socio-psychological phenomenon of the boomerang effect in opinion dynamics. We establish that, under certain conditions on the structure of the signed network that corresponds to the so-called structural balance property, the opinions in the network polarize. Compared to other models in the literature, our model displays a richer and perhaps more intuitive behavior of the opinions when the social network does not satisfy structural balance. In particular, we analyze signed networks in which the opinions show persistent fluctuations (including the case of the so-called clustering balance).

cs.SI↗

arXiv2017

Location Privacy in Mobile Edge Clouds: A Chaff-based Approach

In this paper, we consider user location privacy in mobile edge clouds (MECs). MECs are small clouds deployed at the network edge to offer cloud services close to mobile users, and many solutions have been proposed to maximize service locality by migrating services to follow their users. Co-location of a user and his service, however, implies that a cyber eavesdropper observing service migrations between MECs can localize the user up to one MEC coverage area, which can be fairly small (e.g., a femtocell). We consider using chaff services to defend against such an eavesdropper, with focus on strategies to control the chaffs. Assuming the eavesdropper performs maximum likelihood (ML) detection, we consider both heuristic strategies that mimic the user's mobility and optimized strategies designed to minimize the detection or tracking accuracy. We show that a single chaff controlled by the optimal strategy or its online variation can drive the eavesdropper's tracking accuracy to zero when the user's mobility is sufficiently random. We further propose extended strategies that utilize randomization to defend against an advanced eavesdropper aware of the strategy. The efficacy of our solutions is verified through both synthetic and trace-driven simulations.

cs.DC↗

arXiv2015

Information Cascades in Feed-based Networks of Users with Limited Attention

We build a model of information cascades on feed-based networks, taking into account the finite attention span of users, message generation rates and message forwarding rates. Using this model, we study through simulations, the effect of the extent of user attention on the probability that the cascade becomes viral. In analogy with a branching process, we estimate the branching factor associated with the cascade process for different attention spans and different forwarding probabilities, and demonstrate that beyond a certain attention span, critical forwarding probabilities exist that constitute a threshold after which cascades can become viral. The critical forwarding probabilities have an inverse relationship with the attention span. Next, we develop a semi-analytical approach for our model, that allows us determine the branching factor for given values of message generation rates, message forwarding rates and attention spans. The branching factors obtained using this analytical approach show good agreement with those obtained through simulations. Finally, we analyze an event specific dataset obtained from Twitter, and show that estimated branching factors correlate well with the cascade size distributions associated with distinct hashtags.

physics.soc-ph↗