Search for: All records

Award ID contains: 2312198

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. This article designs a blockchain protocol to mitigate the spread of misinformation in online social networks. The blockchain protocol processes social media postings as transactions, with misinformation being treated as double-spend attacks. The probability and duration for a double-spend attack to succeed within the blockchain protocol are used to compute the misinformation propagation time distribution. Our findings indicate that the rate of misinformation propagation in blockchainbased online social networks is inversely correlated with the fraction of honest miners who reject double-spend attacks. To further analyze the dynamics of misinformation propagation, we employ a susceptible–infectious–recovered (SIR) model combined with preferential attachment in a multicommunity network, which accounts for homophily and community structure in social networks. Numerical experiments using parameters estimated from real-world Twitter hashtag datasets show that the proposed blockchain protocol can reduce the number of users exposed to misinformation by delaying its propagation. 
    more » « less
    Free, publicly-accessible full text available February 1, 2027
  2. In this paper, we model and analyze how a network of interacting LLMs performs collaborative question-answering (CQA) in order to estimate a ground truth given a distributed set of documents. This problem is interesting because LLMs often hallucinate when direct evidence to answer a question is lacking, and these effects become more pronounced in a network of interacting LLMs. The hallucination spreads, causing previously accurate LLMs to hallucinate. We study interacting LLMs and their hallucination by combining novel ideas of mean-field dynamics (MFD) from network science and the randomized utility model from economics to construct a useful generative model. We model the LLM with a latent state that indicates if it is truthful or not with respect to the ground truth, and extend a tractable analytical model considering an MFD to model the diffusion of information in a directed network of LLMs. To specify the probabilities that govern the dynamics of the MFD, we propose a randomized utility model. For a network of LLMs, where each LLM has two possible latent states, we posit sufficient conditions for the existence and uniqueness of a fixed point and analyze the behavior of the fixed point in terms of the incentive (e.g., test-time compute) given to individual LLMs. We experimentally study and analyze the behavior of a network of 100 open-source LLMs with respect to data heterogeneity, node capability, network structure, and sensitivity to framing on multiple semi-synthetic datasets. 
    more » « less
    Free, publicly-accessible full text available February 1, 2027
  3. Multiagent inverse reinforcement learning (IRL) aims to identify Pareto-efficient behavior in a multiagent system, and reconstruct utility functions of the individual agents. Motivated by the problem of detecting UAV (drone) coordination, how can we construct a statistical detector for Pareto-efficient behavior given noisy measurements of the decisions of a multiagent system? This article approaches this IRL problem by deriving necessary and sufficient conditions for a dataset of multiagent system dynamics to be consistent with Pareto-efficient co- ordination, and providing algorithms for recovering utility functions, which are consistent with the system dynamics. We derive an opti- mal statistical detector for determining Pareto-efficient coordination from noisy system measurements, which minimizes Type-I statistical detection error. Then, we provide a utility estimation algorithm, which minimizes the worst case estimation error over a statistical ambiguity set centered at empirical observations; this min–max solution achieves distributionally robust IRL, which is crucial in adversarial strategic interactions. We illustrate these results in a detailed example for detecting Pareto-efficient coordination among multiple UAVs given noisy measurement recorded at a radar. We then reconstruct the utility functions of the UAVs in a distributionally robust sense. 
    more » « less
    Free, publicly-accessible full text available January 1, 2027
  4. Estimating the clutter-plus-noise covariance matrix in highdimensional space-time adaptive processing is challenging in the presence of internal clutter motion (ICM) and a high noise floor. The problem becomes more difficult in low-sample regimes, where the sample covariance matrix becomes ill-conditioned. To capture the ICM and high noise floor, we model the covariance matrix using a “Banded+Spiked” structure. Since the maximum likelihood estimation for this model is nonconvex, we propose a convex relaxation, which is formulated as a Frobenius norm minimization with nonsmooth convex constraints enforcing banded sparsity. This relaxation serves as a provable upper bound for the nonconvex likelihood maximization and extends to cases where the covariance matrix dimension exceeds the number of samples. We derive a variational inequality-based bound to assess its quality. We introduce an algorithm to jointly estimate the banded clutter covariance and noise power. In addition, we establish conditions ensuring the estimated covariance matrix remains positive definite and the bandsize is accurately recovered. Numerical results using the high-fidelity RFView radar simulation environment demonstrate that our algorithm achieves a higher signal-to-clutterplus-noise ratio than state-of-the-art methods, including tapered or banded shrinkage covariance, spiked covariance Stein shrinkage, and diagonal loading, particularly when the covariance matrix dimension exceeds the number of samples. 
    more » « less
    Free, publicly-accessible full text available January 1, 2027
  5. This paper provides a finite-sample analysis of a passive stochastic gradient Langevin dynamics (PSGLD) algo- rithm. This algorithm is designed to achieve adaptive inverse reinforcement learning (IRL). Adaptive IRL aims to estimate the cost function of a forward learner performing a stochastic gradient algorithm (e.g., policy gradient reinforcement learning) by observing their estimates in real-time. The PSGLD algorithm is considered passive because it incorporates noisy gradients provided by an external stochastic gradient algorithm (forward learner), of which it has no control. The PSGLD algorithm acts as a randomized sampler to achieve adaptive IRL by reconstructing the forward learner’s cost function nonparametrically from the stationary measure of a Langevin diffusion. This paper analyzes the non-asymptotic (finite-sample) performance; we provide explicit bounds on the 2-Wasserstein distance between PSGLD algorithm sample measure and the stationary measure encoding the cost function, and provide guarantees for a kernel density estimation scheme which reconstructs the cost function from empirical samples. Our analysis uses tools from the study of Markov diffusion operators. The derived bounds have both practical and theoretical significance. They provide finite-time guarantees for an adaptive IRL mechanism, and substantially generalize the analytical framework of a line of research in passive stochastic gradient algorithms. 
    more » « less
  6. How to design a Markov decision process (MDP)-based radar controller that makes small sacrifices in performance to mask its sensing plan from an adversary? The radar controller purposefully minimizes the Fisher information of its emissions so that an adversary cannot identify the controller’s model parameters accurately. Unlike classical open-loop statistical inference, where the Fisher information serves as a lower bound for the achievable covariance, this article employs the Fisher information as a design constraint for a closed-loop radar controller to mask its sensing plan. We analytically derive a closed-form expression for the determinant of the Fisher informa- tion matrix (FIM) pertaining to the parameters of the MDP-based controller. Subsequently, we formulate an MDP, which is regularized by the determinant of the adversary’s FIM. This results in the per- turbations to the total cost of operation, state–action costs, and the transition matrix. In addition, we propose a maximum-entropy-based convex lower bound for the FIM-constrained MDP, whose solution can serve as an initialization point for the proposed nonlinear optimization problem. This convex lower bound aligns with existing work that employs the same maximum entropy criteria to mask the sensing plan. Numerical results show that the introduction of minor perturbations to the MDP’s state–action costs, transition kernel, and the total operation cost can reduce the Fisher information of the emissions. Consequently, this reduction amplifies the variability in policy and transition kernel estimation errors, thwarting the adversary’s accuracy in estimating the controller’s sensing plan. We demonstrate this by comparing the error in the estimate of the transition kernel under different criteria: the FIM criteria, the maximum entropy criteria, a sensing plan where actions are chosen uniformly, and the unmasked sensing plan. 
    more » « less
  7. How can non-communicating agents learn to share congested resources efficiently? This is a challeng- ing task when the agents can access the same resource simultaneously (in contrast to multi-agent multi-armed bandit problems) and the resource valuations differ among agents. We present a fully distributed algorithm for learning to share in congested environments and prove that the agents’ regret with respect to the optimal allocation is poly-logarithmic in the time horizon. Performance in the non-asymptotic regime is illustrated in numerical simulations. The distributed algorithm has applications in cloud computing and spectrum sharing. 
    more » « less
  8. A learner aims to minimize a function f by repeatedly querying a distributed oracle that provides noisy gradient evaluations. At the same time, the learner seeks to hide arg min f from a malicious eavesdropper that observes the learner’s queries. This paper considers the problem of covert or learner-private optimization, where the learner has to dynamically choose between learning and obfuscation by exploiting the stochasticity. The problem of controlling the stochastic gradient algorithm for covert optimization is modeled as a Markov decision process, and we show that the dynamic programming operator has a supermodular structure implying that the optimal policy has a monotone threshold structure. A computationally efficient policy gradient algorithm is proposed to search for the optimal querying policy without knowledge of the transition probabilities. As a practical application, our methods are demonstrated on a hate speech classification task in a federated setting where an eavesdropper can use the optimal weights to generate toxic content, which is more easily misclassified. Numerical results show that when the learner uses the optimal policy, an eavesdropper can only achieve a validation accuracy of 52% with no information and 69% when it has a public dataset with 10% positive samples compared to 83% when the learner employs a greedy policy. 
    more » « less
  9. Can deep convolutional neural networks (CNNs) for image classification be interpreted as utility maximizers with information costs? By performing set-valued system identifica- tion for Bayesian decision systems, we demonstrate that deep CNNs behave equivalently (in terms of necessary and sufficient conditions) to rationally inattentive Bayesian utility maximizers, a generative model used extensively in economics for human decision-making. Our claim is based on approximately 500 numerical experiments on 5 widely used neural network archi- tectures. The parameters of the resulting interpretable model are computed efficiently via convex feasibility algorithms. As a practical application, we also illustrate how the reconstructed interpretable model can predict the classification performance of deep CNNs with high accuracy. The theoretical foundation of our approach lies in Bayesian revealed preference studied in micro-economics. All our results are on GitHub and completely reproducible. 
    more » « less
  10. This letter studies how a stochastic gradient algorithm (SG) can be controlled to hide the estimate of the local stationary point from an eavesdropper. Such prob- lems are of significant interest in distributed optimization settings like federated learning and inventory management. A learner queries a stochastic oracle and incentivizes the oracle to obtain noisy gradient measurements and per- form SG. The oracle probabilistically returns either a noisy gradient of the function or a non-informative measure- ment, depending on the oracle state and incentive. The learner’s query and incentive are visible to an eavesdropper who wishes to estimate the stationary point. This letter formulates the problem of the learner performing covert optimization by dynamically incentivizing the stochastic oracle and obfuscating the eavesdropper as a finite-horizon Markov decision process (MDP). Using conditions for interval-dominance on the cost and transition probability structure, we show that the optimal policy for the MDP has a monotone threshold structure. We propose searching for the optimal stationary policy with the threshold structure using a stochastic approximation algorithm and a multi– armed bandit approach. The effectiveness of our methods is numerically demonstrated on a covert federated learning hate-speech classification task. 
    more » « less