Interdiction problems arise in a number of application areas, including global security, supply chains, and critical infrastructure protection - the goal is inhibit the movement of goods, people or information. An area of particular interest is counter-narcotics, where nodes or edges in a network are placed under surveillance or blocked to minimize the flow of illicit drugs from source to the destination. A fundamental challenge in this narco-traffic interdiction is data scarcity: available datasets are limited by the very nature of the problem and provide only partial and uncertain views of trafficking networks. Thus, developing robust interdiction methods that take this inherent lack of information is critical. In this paper we initiate the study of network flow interdiction problems under network uncertainty. First, using a limited real-world dataset, we generate an ensemble of plausible network realizations representing alternative trafficking scenarios. The method combines simulations with mathematical programming techniques to generate network ensembles that are consistent with the observed data. Second, we formulate the robust network flow interdiction problem and develop an integer linear program to solve the problem. We evaluate the optimal interdiction strategy and obtain the residual flows over the scenarios. Our analysis reveals that even modest budgets can yield significant flow reductions. However, optimal solutions vary substantially across scenarios, motivating the need for robust solutions. We show that the robust strategy achieves near-optimal performance across all near-real world realizations while remaining stable under structural uncertainty. This simulation-driven approach provides a principled basis for policy analysis and supports maximizing the return on interdiction investments in uncertain, data-limited environments.

Epidemic modeling is essential for public health planning, yet traditional approaches rely on fixed model classes that require manual redesign as pathogens, policies, and scenario assumptions evolve. We introduce EPIAGENT, an agentic framework that automatically synthesizes, calibrates, verifies, and refines epidemiological simulators by modeling disease progression as an iterative program synthesis problem. A central design choice is an explicit epidemiological flow graph intermediate representation that links scenario specifications to model structure and enables strong, modular correctness checks before code is generated. Verified flow graphs are then compiled into mechanistic models supporting interpretable parameter learning under physical and epidemiological constraints. Evaluation on epidemiological scenario case studies demonstrates that EPIAGENT captures complex growth dynamics and produces epidemiologically consistent counterfactual projections across varying vaccination and immune escape assumptions. Our results show that the agentic feedback loop prevents degeneration and significantly accelerates convergence toward valid models by mimicking professional expert workflows.

Methicillin-resistant Staphylococcus aureus (MRSA) is a critical public health threat within hospitals as well as long-term care facilities. Better understanding of MRSA risks, evaluation of interventions and forecasting MRSA rates are important public health problems. Existing forecasting models rely on statistical or neural network approaches, which lack epidemiological interpretability, and have limited performance. Mechanistic epidemic models are difficult to calibrate and limited in incorporating diverse datasets. We present CALYPSO, a hybrid framework that integrates neural networks with mechanistic metapopulation models to capture the spread dynamics of infectious diseases (i.e., MRSA) across healthcare and community settings. Our model leverages patient-level insurance claims, commuting data, and healthcare transfer patterns to learn region- and time-specific parameters governing MRSA spread. This enables accurate, interpretable forecasts at multiple spatial resolutions (county, healthcare facility, region, state) and supports counterfactual analyses of infection control policies and outbreak risks. We also show that CALYPSO improves statewide forecasting performance by over 4.5

Vaccines have proven to be extremely effective in preventing the spread of COVID-19 and potentially ending the pandemic. However, it is impossible to guarantee 100% effectiveness of a vaccine. This is not considered in previous models, which may have a significant impact on the distribution, implementation, and outcome of any preventive measures. In this paper, we study the problem of choosing a set of individuals to vaccinate given a contact network in order to minimize the expected number of infections given that vaccines are not fully effective, by sample averaging and linear programming techniques to achieve approximate solutions. We also consider this model for other variations of the problem, minimizing average and maximum degree of a network. These objectives are often used as proxies for minimizing the total infection in a network, and we show experimentally that the objectives indeed correlate well with the expected number of infections. In addition, we present a greedy approximation algorithm for the two variations of the problem. Lastly, we run experiments on a contact network for the population of Montgomery County, VA in order to investigate the effectiveness and robustness of our algorithms.

We introduce P3CA (PTR-based Private Principal Component Analysis), a one-shot output perturbation mechanism for releasing the top-k eigenspace of a graph’s adjacency matrix under edge differential privacy. Many networked datasets contain sensitive relational information, which requires privacy-preserving computation of spectral representations used as primitives in graph inference and graph machine learning. While differential privacy (DP) is the gold standard for protecting sensitive data, existing DP algorithms for private PCA often suffer from low accuracy due to large noise injection or high computational complexity. P3CA leverages the Propose—Test—Release (PTR) paradigm to design an instance-specific mechanism for privately releasing the top-k eigenspace. Although PTR is computationally intensive in general, our key technical contribution is to design an efficient variant which privately tests whether the input graph is sufficiently stable based on which it releases a noisy projection matrix with noise calibrated to the instance-specific sensitivity. Unlike global-sensitivity-based approaches, this method achieves improved accuracy while remaining highly scalable. We prove that P3CA satisfies (ε ,δ ) -edge differential privacy and establish utility guarantees for the released eigenspace, which can be directly used for downstream tasks such as differentially private spectral clustering and private adjacency spectral embedding without additional privacy cost. Experiments show that P3CA consistently outperforms existing DP spectral methods, achieving lower error for slightly privacy budgets while providing substantial computational gains.

Global supply chains are highly interconnected, making them vulnerable to cascading disruptions induced by trade policy shocks. Understanding how such disruptions propagate through production networks, and how mitigation mechanisms such as trade reallocation and production adjustment can alleviate their impacts, remains a central challenge. In this work, we develop a linear programming formulation of an Input-Output (IO) system that captures cascading supply-chain disruptions together with trade reallocation and production expansion. Our formulation yields a system-level equilibrium characterization that enables the joint analysis of disruption propagation and mitigation within a unified framework. We propose an efficient algorithm for computing approximate equilibrium solutions by minimizing total unmet demand in large IO systems. We apply our approach to tariff-induced disruptions in the global oilseeds supply chain arising from the U.S.-China trade war. Our results show that a localized 70

A key public health problem during an outbreak is to reconstruct the disease cascade from a partial set of confirmed infections. This has been studied extensively under the Maximum Likelihood Estimation (MLE) formulation, which reduces the problem to finding some type of Steiner subgraph on a network. Group surveillance like wastewater or aerosol monitoring is a form of mass/pooled testing where samples from multiple individuals are pooled together and tested once for all. While a single negative test clears multiple individuals, a positive test does not reveal the infected individuals in the test pool. We introduce the POOLCASCADEMLE problem in the setting of a network propagation process, where the goal is to find a MLE cascade subgraph which is consistent with the pooled test outcomes. Previous work on reconstruction assumes that the test results are of individuals, i.e., pools of size one, and requires a consistent cascade to connect the positive testing nodes. In POOLCASCADEMLE, a consistent cascade must choose at least one node in each positive pool, adding another combinatorial layer. We show that, under the Independent Cascade (IC) model, POOLCASCADEMLE is NP-hard, and present an approximation algorithm based on a reduction to the Group Steiner Tree problem. We also consider a one-hop version of this problem, in which the disease can spread for one time step after being seeded. We show that even this restricted version is NP-hard, and develop a method using linear programming relaxation and rounding. We evaluate the performance of our methods on real and synthetic contact networks, in terms of missing infection recovery and prevalence estimation. We find that our approach outperforms meaningful baselines which correspond to pools of size one and use state-of-the-art methods.

The US Centers for Disease Control and Prevention (CDC), in 2019, designated Methicillin-resistant Staphylococcus aureus (MRSA) as a serious antimicrobial resistance threat. The risk of acquiring MRSA and suffering life-threatening consequences due to it remains especially high for hospitalized patients due to a unique combination of factors, including: co-morbid conditions, immuno suppression, antibiotic use, and risk of contact with contaminated hospital workers and equipment. In this paper, we present a novel generative probabilistic model, GenHAI, for modeling sequences of MRSA test results outcomes for patients during a single hospitalization. This model can be used to answer many important questions from the perspectives of hospital administrators for mitigating the risk of MRSA infections. Our model is based on the probabilistic programming paradigm, and can be used to approximately answer a variety of predictive, causal, and counterfactual questions. We demonstrate the efficacy of our model by comparing it against discriminative and generative machine learning models using two real-world datasets.

The existing methods for evaluating the medical knowledge of Large Language Models (LLMs) are largely based on atemporal examination-style benchmarks, while in reality, medical knowledge is inherently dynamic and continuously evolves as new evidence emerges and treatments are approved. Consequently, evaluating medical knowledge without a temporal context may provide an incomplete assessment of whether LLMs can accurately reason about time-specific medical knowledge. Moreover, most medical data are historical, requiring the models not only to recall the correct knowledge, but also to know when that knowledge is correct. To bridge the gap, we built TempoMed-Bench, the first-of-its-kind benchmark for evaluating the temporal awareness of the LLMs in the medical domain through evolving guideline knowledge. Based on the TempoMed-Bench, our evaluation analysis first reveals that LLMs lack temporal awareness in medical knowledge through the key findings: (1) model performance on up-to-date medical knowledge exhibits a gradual linear decline over time rather than a sharp knowledge-cutoff behavior, suggesting that parametric medical knowledge is not strictly bounded by knowledge cutoffs; (2) LLMs consistently struggle more with recalling outdated historical medical knowledge than with up-to-date recommendations: accuracy of historical knowledge is only 25.37

Computing the principal component (PC) of the adjacency matrix of an undirected graph has several applications ranging from identifying key vertices for influence maximization and controlling diffusion processes, to discovering densely interconnected vertex subsets. However, many networked datasets are sensitive, which necessitates private computation of the PC for use in the aforementioned applications. Differential privacy has emerged as the gold standard in privacy-preserving data analysis, but existing DP algorithms for private PC suffer from low accuracy due to large noise injection or high complexity. Motivated by the large gap between the local and global sensitivities of the PC on real-graphs, we consider instance-specific mechanisms for privately computing the PC under edge-DP. These mechanisms guarantee privacy for all datasets, but provide good utility on “well-behaved” datasets by injecting smaller amounts of noise. More specifically, we consider the Propose-Test-Release (PTR) framework. Although computationally expensive in general, we design a novel approach for implementing a PTR variant in the same time as computation of a non-private PC, while offering good utility. Our framework tests in a differentially-private manner whether a given graph is “well-behaved” or not, and then tests whether its private to release a noisy PC with small noise. As a consequence, this also leads to the first DP algorithm for the Densest-k-subgraph problem, a key graph mining primitive. We run our method on diverse real-world networks, with the largest having 3 million vertices, and compare its utility to a pre-existing baseline based on the private power method (PPM). Although PTR requires a slightly larger privacy budget, on average, it achieves a 180-fold improvement in runtime over PPM.

Generation of clear and accessible public health narratives is critical for communicating complex epidemiological projections to policymakers and the general public at large. Such narratives require more than simply reporting numbers: projections must be contextualized and quantitatively grounded across multiple dimensions. Further, projections are often derived from large ensemble datasets which combine intervention assumptions, geographic and demographic strata, outcomes, time horizons, and uncertainty quantiles. However, directly using large language models (LLMs) to summarize and contextualize such data often leads to inconsistencies, omissions, and fragile behavior. We introduce an agentic framework (EpiNarrate) for public health report generation that separates structured numerical reasoning from natural-language generation. The framework first extracts scenario axes and organizes them into a partial-order schema, enabling systematic traversal of the underlying multidimensional space. It then constructs an augmented dataset and derives valid quantitative statements through a comparison grammar that enforces semantic and arithmetic consistency. To balance coverage and non-redundancy, we introduce an interestingness-driven selection mechanism based on maximum-entropy principles. Experiments on the COVID-19 Scenario Modeling Hub demonstrate that our model produces narratives with improved factual grounding and broader coverage of salient epidemiological patterns, while preserving the style of expert-written reports.

In advance of an approaching hurricane, residents must prepare and make decisions. Families might need windows boarded up before the storm and fallen trees removed afterward. Those sheltering in place may need additional resources, such as generators, food, potable water, and access to healthcare. Local governments may provide information at a municipality level, but sharing awareness about more proximate hazards may be beyond their capabilities. We developed a web application, StormShare, to assist with these and other needs, contributing to capacity building for social resiliency. Developed with guidance from domain experts, three Florida municipalities, and a focus group, with further refinements recommended by two additional focus groups, StormShare depends on crowdsourcing, whereby users provide information to facilitate cooperation through community involvement. Users can post about where goods can be found, services they are willing to provide, and localized alerts, while other users rely on these posts to make informed decisions. In this paper, we describe StormShare, explore some of the considerations of developing a crowdsourcing application for hurricane preparedness, and offer recommendations for future improvements.

Accurate clinical outcome prediction using Electronic Health Records (EHRs) is crucial for patient care and resource allocation. EHRs include both structured data and rich, unstructured clinical notes. However, prior machine learning methods struggle with the multi-modality, long context of notes, and severe class imbalance in clinical tasks. To introduce and evaluate KAMELEON (Knowledge-Augmented Multimodal EHR LEarning for Outcome predictioN), a unified, two-stage hybrid framework that integrates diverse EHR modalities and external biomedical knowledge to enhance clinical risk prediction This study used the publicly available, de-identified MIMIC-III dataset, which includes structured and unstructured data for over 40,000 Intensive Care Unit (ICU) patients. The two tasks studied were 30-day readmission (approximately 4% positive rate) and in-hospital mortality prediction (approximately 13% positive rate). Train-test splits were patient-disjoint (80:20). Performance was evaluated against general and medical Large Language Models (LLMs) and structured baselines. Key metrics included the Area Under the Receiver Operating Characteristic curve (AUROC), Area Under the Precision-Recall Curve (AUPRC), and Macro F1-score. The KAMELEON framework consistently outperformed all existing baselines. • 30-Day Readmission. The KAMELEON-BalancedRF model achieved an AUROC of 0.845 and a Sensitivity (Recall) of 0.79. Ablation analysis demonstrated the critical role of the LLM-generated reasoning, with its removal causing the AUROC to drop from 0.844 to 0.7 and sensitivity to fall by over 80%. • In-Hospital Mortality: The KAMELEON-XGBoost model achieved an AUROC of 0.92 and an AUPRC of 0.650. Unstructured-only models showed limited ability to discern mortality, with AUROC values near chance (around 0.51–0.53). KAMELEON is the first systematic framework to enhance LLMs for healthcare prediction through graph-guided knowledge retrieval combined with structured machine learning. The framework demonstrates superior performance across both prediction tasks, highlighting the synergistic value of combining diverse data modalities and LLM reasoning for robust clinical risk estimation.

Accurate prediction of clinical outcomes using Electronic Health Records (EHRs) is critical for early intervention, efficient resource allocation, and improved patient care. EHRs contain multimodal data, including both structured data and unstructured clinical notes that provide rich, context-specific information. In this work, we introduce a unified framework that seamlessly integrates these diverse modalities, leveraging all relevant available information through a two-stage architecture for clinical risk prediction. In the first stage, a fine-tuned Large Language Model (LLM) extracts crucial, task-relevant information from clinical notes, which is enhanced by graph-based retrieval of external domain knowledge from sources such as a medical corpus like PubMed, grounding the LLM's understanding. The second stage combines both unstructured representations and features derived from the structured data to generate the final predictions. This approach supports a wide range of clinical tasks. Here, we demonstrate its effectiveness on 30-day readmission and in-hospital mortality prediction. Experimental results show that our framework achieves strong performance, with AUC scores of 0.84 and 0.92, respectively, despite these tasks involving severely imbalanced datasets, with positive rates ranging from approximately 4% to 13%. Moreover, it outperforms all existing baselines and clinical practices, including established risk scoring systems. To the best of our knowledge, this is one of the first frameworks for healthcare prediction which enhances the power of an LLM-based graph-guided knowledge retrieval method by combining it with structured data for improved clinical outcome prediction.

We study exascale parallel algorithms for the selection of intervention or monitoring strategies in massive realistic socio-technical networks through scalable Influence Maximization (InfMax) algorithms. We employ novel techniques to enable efficient scaling on up to 8k nodes of OLCF Frontier, with 65k AMD GPUs and 458k AMD CPU cores. Current state-of-the-art InfMax tools are limited to networks with only a few million actors (vertices) and a few hundred million interactions (edges). By overcoming these limitations,

The administration of the Measles, Mumps, and Rubella (MMR) vaccination has had a substantial impact on controlling the spread of measles on a global scale. Nevertheless, the COVID-19 pandemic caused major disruptions to normal immunization schedules, causing the omission or delay of routine immunizations. Expanding on previous research that simulated measles outbreaks using a detailed agent-based model, this study integrates epidemiological forecasts with spatial econometrics analysis. Our objective is to quantify the household-level direct and indirect health and economic impact of measles outbreaks caused by reduction in MMR vaccine uptake. A network-based SEIR (susceptible-exposed-infected-recovered) model is used to simulate the transmission of measles over a synthetic social contact network of Virginia, under various scenarios. Household-level costs of measles outbreak, encompassing MMR vaccine expenses, treatment costs, and productivity losses, are estimated from the simulation results. A Generalized Spatial Autoregressive (GSAR) model is used to estimate the spatial ‘spillover effect’ on neighboring counties. Our findings indicate that reduced MMR vaccination rates are associated with increased measles cases and related economic costs, which are intensified by disease transmissibility and moderated by home quarantine. The GSAR model, with spatial lag coefficients, shows significant spatial interdependencies. A small decrease in vaccination rate in an urban region like Richmond, Virginia, has significant economic and epidemiological spillover effect, while similar reductions in rural regions like Highland County, Virginia, have a negligible impact. A decline in MMR vaccination rate has ramifications for both disease incidence and the economy, presenting diverse consequences influenced by regional disparities. Policymakers should acknowledge the interconnectedness of health and economic outcomes across regions. This research underscores the necessity of implementing broad, region-wide policy measures in response to fluctuations in vaccination rates, prioritizing overarching strategies over localized interventions.

This paper presents a novel approach to Explainable AI (XAI) that combines contrastive explanations with differential privacy for clustering algorithms. Focusing on k-median and k-means problems, we calculate contrastive explanations as the utility difference between original clustering and clustering with a centroid fixed to a specific data point. This method provides personalized insights into centroid placement. Our key contribution is demonstrating that these differentially private explanations achieve essentially the same utility bounds as non-private explanations. Experiments across various datasets show that our approach offers meaningful, privacy-preserving, and individually relevant explanations without significantly compromising clustering utility. This work advances privacy-aware machine learning by balancing data protection, explanation quality, and personalization in clustering tasks.

Diffusion models are vulnerable to backdoor attacks, where malicious attackers inject backdoors by poisoning certain training samples during the training stage. This poses a significant threat to real-world applications in the Model-as-a-Service (MaaS) scenario, where users query diffusion models through APIs or directly download them from the internet. To mitigate the threat of backdoor attacks under MaaS, black-box input-level backdoor detection has drawn recent interest, where defenders aim to build a firewall that filters out backdoor samples in the inference stage, with access only to input queries and the generated results from diffusion models. Despite some preliminary explorations on the traditional classification tasks, these methods cannot be directly applied to the generative tasks due to two major challenges: (1) more diverse failures and (2) a multi-modality attack surface. In this paper, we propose a black-box input-level backdoor detection framework on diffusion models, called UFID. Our defense is motivated by an insightful causal analysis: Backdoor attacks serve as the confounder, introducing a spurious path from input to target images, which remains consistent even when we perturb the input samples with Gaussian noise. We further validate the intuition with theoretical analysis. Extensive experiments across different datasets on both conditional and unconditional diffusion models show that our method achieves superb performance on detection effectiveness and run-time efficiency.

Consider public health officials aiming to spread awareness about a new vaccine in a community interconnected by a social network. How can they distribute information with minimal resources, so as to avoid polarization and ensure community-wide convergence of opinion? To tackle such challenges, we initiate the study of sample complexity of opinion formation in networks. Our framework is built on the recognized opinion formation game, where we regard each agent’s opinion as a data-derived model, unlike previous works that treat opinions as data-independent scalars. The opinion model for every agent is initially learned from its local samples and evolves game-theoretically as all agents communicate with neighbors and revise their models towards an equilibrium. Our focus is on the sample complexity needed to ensure that the opinions converge to an equilibrium such that every agent’s final model has low generalization error. Our paper has two main technical results. First, we present a novel polynomial time optimization framework to quantify the total sample complexity for arbitrary networks, when the underlying learning problem is (generalized) linear regression. Second, we leverage this optimization to study the network gain which measures the improvement of sample complexity when learning over a network compared to that in isolation. Towards this end, we derive network gain bounds for various network classes including cliques, star graphs, and random regular graphs. Additionally, our framework provides a method to study sample distribution within the network, suggesting that it is sufficient to allocate samples inversely to the degree. Empirical results on both synthetic and real-world networks strongly support our theoretical findings.

Epidemic analyses increasingly rely on heterogeneous datasets, many of which are sensitive and require strong privacy protection. Although differential privacy (DP) has become a standard in machine learning and data sharing, its adoption in epidemiological modeling remains limited. In this work, we introduce DPEpiNN, a unified framework that integrates deep neural networks with a mechanistic SEIRM-based metapopulation model under formal DP guarantees. DPEpiNN supports multiple epidemic tasks (including multi-step forecasting, nowcasting, effective reproduction number (R_t) estimation, and intervention analysis) within a single differentiable pipeline. The framework jointly learns epidemic parameters from heterogeneous public and sensitive datasets, while ensuring privacy via input perturbation mechanisms. We evaluate DPEpiNN using COVID-19 data from three regions. Results show that incorporating sensitive datasets substantially improves predictive performance even under strong privacy constraints. Compared with a deep learning baseline, DPEpiNN achieves higher accuracy in forecasting and nowcasting while producing reliable estimates of R_t. Furthermore, the learned epidemic transmission models remain inherently private due to the post-processing property of differential privacy, enabling downstream policy analyses such as simulation of social distancing interventions. Our work demonstrates that interpretability (through mechanistic modeling), predictive accuracy (through neural integration), and rigorous privacy guarantees can be jointly achieved in modern epidemic modeling.