arXiv subjects

Nasimeh Heydaribeni

Publications and source records attributed to Nasimeh Heydaribeni.

11 recordsLinked to original sources

arXiv2024

Magmaw: Modality-Agnostic Adversarial Attacks on Machine Learning-Based Wireless Communication Systems

Machine Learning (ML) has been instrumental in enabling joint transceiver optimization by merging all physical layer blocks of the end-to-end wireless communication systems. Although there have been a number of adversarial attacks on ML-based wireless systems, the existing methods do not provide a comprehensive view including multi-modality of the source data, common physical layer protocols, and wireless domain constraints. This paper proposes Magmaw, a novel wireless attack methodology capable of generating universal adversarial perturbations for any multimodal signal transmitted over a wireless channel. We further introduce new objectives for adversarial attacks on downstream applications. We adopt the widely-used defenses to verify the resilience of Magmaw. For proof-of-concept evaluation, we build a real-time wireless attack platform using a software-defined radio system. Experimental results demonstrate that Magmaw causes significant performance degradation even in the presence of strong defense mechanisms. Furthermore, we validate the performance of Magmaw in two case studies: encrypted communication channel and channel modality-based ML model.

cs.CR↗

arXiv2024

Distributed Constrained Combinatorial Optimization leveraging Hypergraph Neural Networks

Scalable addressing of high dimensional constrained combinatorial optimization problems is a challenge that arises in several science and engineering disciplines. Recent work introduced novel application of graph neural networks for solving quadratic-cost combinatorial optimization problems. However, effective utilization of models such as graph neural networks to address general problems with higher order constraints is an unresolved challenge. This paper presents a framework, HypOp, which advances the state of the art for solving combinatorial optimization problems in several aspects: (i) it generalizes the prior results to higher order constrained problems with arbitrary cost functions by leveraging hypergraph neural networks; (ii) enables scalability to larger problems by introducing a new distributed and parallel training architecture; (iii) demonstrates generalizability across different problem formulations by transferring knowledge within the same hypergraph; (iv) substantially boosts the solution accuracy compared with the prior art by suggesting a fine-tuning step using simulated annealing; (v) shows a remarkable progress on numerous benchmark examples, including hypergraph MaxCut, satisfiability, and resource allocation problems, with notable run time improvements using a combination of fine-tuning and distributed training techniques. We showcase the application of HypOp in scientific discovery by solving a hypergraph MaxCut problem on NDC drug-substance hypergraph. Through extensive experimentation on various optimization problems, HypOp demonstrates superiority over existing unsupervised learning-based solvers and generic optimization methods.

math.OC↗

arXiv2024

Assigning Entities to Teams as a Hypergraph Discovery Problem

We propose a team assignment algorithm based on a hypergraph approach focusing on resilience and diffusion optimization. Specifically, our method is based on optimizing the algebraic connectivity of the Laplacian matrix of an edge-dependent vertex-weighted hypergraph. We used constrained simulated annealing, where we constrained the effort agents can exert to perform a task and the minimum effort a task requires to be completed. We evaluated our methods in terms of the number of unsuccessful patches to drive our solution into the feasible region and the cost of patching. We showed that our formulation provides more robust solutions than the original data and the greedy approach. We hope that our methods motivate further research in applying hypergraphs to similar problems in different research areas and in exploring variations of our methods.

cs.SI↗

arXiv2024

SureFED: Robust Federated Learning via Uncertainty-Aware Inward and Outward Inspection

In this work, we introduce SureFED, a novel framework for byzantine robust federated learning. Unlike many existing defense methods that rely on statistically robust quantities, making them vulnerable to stealthy and colluding attacks, SureFED establishes trust using the local information of benign clients. SureFED utilizes an uncertainty aware model evaluation and introspection to safeguard against poisoning attacks. In particular, each client independently trains a clean local model exclusively using its local dataset, acting as the reference point for evaluating model updates. SureFED leverages Bayesian models that provide model uncertainties and play a crucial role in the model evaluation process. Our framework exhibits robustness even when the majority of clients are compromised, remains agnostic to the number of malicious clients, and is well-suited for non-IID settings. We theoretically prove the robustness of our algorithm against data and model poisoning attacks in a decentralized linear regression setting. Proof-of Concept evaluations on benchmark image classification data demonstrate the superiority of SureFED over the state of the art defense methods under various colluding and non-colluding data and model poisoning attacks.

cs.LG↗

arXiv2022

Do Informational Cascades Happen with Non-myopic Agents?

We consider an environment where players need to decide whether to buy a certain product (or adopt a technology) or not. The product is either good or bad, but its true value is unknown to the players. Instead, each player has her own private information on its quality. Each player can observe the previous actions of other players and estimate the quality of the product. A classic result in the literature shows that in similar settings informational cascades occur where learning stops for the whole network and players repeat the actions of their predecessors. In contrast to this literature, in this work, players get more than one opportunity to act. In each turn, a player is chosen uniformly at random from all players and can decide to buy the product and leave the market or wait. Her utility is the total expected discounted reward, and thus myopic strategies may not constitute equilibria. We provide a characterization of perfect Bayesian equilibria (PBE) with forward-looking strategies through a fixed-point equation of dimensionality that grows only quadratically with the number of players. Using this tractable fixed-point equation, we show the existence of a PBE and characterize PBE with threshold strategies. Based on this characterization we study informational cascades in two regimes. First, we show that for a discount factor δ strictly smaller than one, informational cascades happen with high probability as the number of players N increases. Furthermore, only a small portion of the total information in the system is revealed before a cascade occurs ...

econ.GN↗

arXiv2021

Information Design for a Non-atomic Service Scheduling Game

We study an information design problem for a non-atomic service scheduling game. The service starts at a random time and there is a continuum of agent population who have a prior belief about the service start time but do not observe the actual realization of it. The agents want to make decisions of when to join the queue in order to avoid long waits in the queue or not to arrive earlier than the service has started. There is a planner who knows when the service starts and makes suggestions to the agents about when to join the queue through an obedient direct signaling strategy, in order to minimize the average social cost. We characterize the full information and the no information equilibria and we show in what conditions it is optimal for the planner to reveal the full information to the agents. Further, by imposing appropriate assumptions on the model, we formulate the information design problem as a generalized problem of moments (GPM) and use computational tools developed for such problems to solve the problem numerically.

eess.SY↗

arXiv2021

Joint Information and Mechanism Design for Queues with Heterogeneous Users

We consider a queue with an unobservable backlog by the incoming users. There is an information designer that observes the queue backlog and makes recommendations to the users arriving at the queue whether to join or not to join the queue. The arriving users have payoff relevant private types. The users, upon arrival, send a message, that is supposed to be their type, to the information designer if they are willing to hear a recommendation. The information designer then creates a recommendation for that specific type of user. The users have to pay a tax in exchange for the information they receive. In this setting, the information designer has two types of commitments. The first commitment is the recommendation policy and the second commitment is the tax function. We combine mechanism design and information design to study a queuing system with heterogeneous users. In this setting, the information designer is a sender of the information in the information design aspect and a receiver in the mechanism design aspect of the model. We formulate an optimization problem that characterizes the solution of the joint design problem. We characterize the tax functions and provide structural results for the recommendation policy of the information designer.

eess.SY↗

arXiv2020

Structured Equilibria for Dynamic Games with Asymmetric Information and Dependent Types

We consider a dynamic game with asymmetric information where each player observes privately a noisy version of a (hidden) state of the world V, resulting in dependent private observations. We study structured perfect Bayesian equilibria that use private beliefs in their strategies as sufficient statistics for summarizing their observation history. The main difficulty in finding the appropriate sufficient statistic (state) for the structured strategies arises from the fact that players need to construct (private) beliefs on other players' private beliefs on V, which in turn would imply that an infinite hierarchy of beliefs on beliefs needs to be constructed, rendering the problem unsolvable. We show that this is not the case: each player's belief on other players' beliefs on V can be characterized by her own belief on V and some appropriately defined public belief. We then specialize this setting to the case of a Linear Quadratic Gaussian (LQG) non-zero-sum game and we characterize linear structured PBE that can be found through a backward/forward algorithm akin to dynamic programming for the standard LQG control problem. Unlike the standard LQG problem, however, some of the required quantities for the Kalman filter are observation-dependent and thus cannot be evaluated off-line through a forward recursion.

eess.SY↗

arXiv2019

Distributed Mechanism Design for Network Resource Allocation Problems

In the standard Mechanism Design framework, agents' messages are gathered at a central point and allocation/tax functions are calculated in a centralized manner, i.e., as functions of all network agents' messages. This requirement may cause communication and computation overhead and necessitates the design of mechanisms that alleviate this bottleneck. We consider a scenario where message transmission can only be performed locally so that the mechanism allocation/tax functions can be calculated in a decentralized manner. Each agent transmits messages to her local neighborhood, as defined by a given message-exchange network, and her allocation/tax functions are only functions of the available neighborhood messages. This scenario gives rise to a novel research problem that we call "Distributed Mechanism Design". In this paper, we propose two distributed mechanisms for network utility maximization problems that involve private and public goods with competition and cooperation between agents. As a concrete example, we use the problems of rate allocation in networks with either unicast or multirate multicast transmission protocols. The proposed mechanism for each of the protocols fully implements the optimal allocation in Nash equilibria and its message space dimensionality scales linearly with respect to the number of agents in the network.

cs.GT↗

arXiv2019

Linear Equilibria for Dynamic LQG Games with Asymmetric Information and Dependent Types

We consider a non-zero-sum linear quadratic Gaussian (LQG) dynamic game with asymmetric information. Each player observes privately a noisy version of a (hidden) state of the world $V$, resulting in dependent private observations. We study perfect Bayesian equilibria (PBE) for this game with equilibrium strategies that are linear in players' private estimates of $V$. The main difficulty arises from the fact that players need to construct estimates on other players' estimate on $V$, which in turn would imply that an infinite hierarchy of estimates on estimates needs to be constructed, rendering the problem unsolvable. We show that this is not the case: each player's estimate on other players' estimates on $V$ can be summarized into her own estimate on $V$ and some appropriately defined public information. Based on this finding we characterize the PBE through a backward/forward algorithm akin to dynamic programming for the standard LQG control problem. Unlike the standard LQG problem, however, Kalman filter covariance matrices, as well as some other required quantities, are observation-dependent and thus cannot be evaluated off-line through a forward recursion.

econ.GN↗

arXiv2019

Distributed Mechanism Design for Multicast Transmission

In the standard Mechanism Design framework (Hurwicz-Reiter), there is a central authority that gathers agents' messages and subsequently determines the allocation and tax for each agent. We consider a scenario where, due to communication overhead and other constraints, such broadcasting of messages to a central authority cannot take place. Instead, only local message exchange is allowed between agents. As a result, each agent should be able to determine her own allocation and tax based on the messages in the local neighborhood, as defined by a given message graph describing the communication constraints. This scenario gives rise to a novel research direction that we call "Distributed Mechanism Design". In this paper, we propose such a distributed mechanism for the problem of rate allocation in a multicast transmission network. The proposed mechanism fully implements the optimal allocation in Nash equilibria and its message space dimension is linear with respect to the number of agents in the network.

cs.GT↗