Bradley Malin

Weixin Liu, Congning Ni, Shelagh A. Mulvaney et al.

Large language models (LLMs) are increasingly used in the mental health domain, yet it remains unclear how well they capture related biomedical knowledge and how reliably they apply it to clinically salient structured judgments. Here, we present a knowledge-graph (KG)-grounded benchmark for assessing LLMs on mental-health entity recognition, relation judgment, and two-hop reasoning. The benchmark is derived from PrimeKG and comprises nine task families with KG-supported answers and controlled negative options. Experiments across 15 closed- and open-source LLMs reveal a persistent recognition-to-judgment gap: leading models achieve near-ceiling performance on entity typing and on the small relation-typing subset, yet they still struggle with relation prediction and two-hop reasoning. Additionally, short KG-derived snippets benefit some models but degrade performance for others. Moreover, output-format reliability can substantially influence measured performance under constrained multiple-choice settings, highlighting the critical role of response validity in benchmark-based evaluation. MHGraphBench should therefore be interpreted as evaluating agreement with a curated mental-health slice of PrimeKG under a constrained multiple-choice interface, rather than as a direct assessment of real-world clinical safety.

Chao Yan, Yao Yan, Zhiyu Wan et al.

Synthetic health data have the potential to mitigate privacy concerns when sharing data to support biomedical research and the development of innovative healthcare applications. Modern approaches for data generation based on machine learning, generative adversarial networks (GAN) methods in particular, continue to evolve and demonstrate remarkable potential. Yet there is a lack of a systematic assessment framework to benchmark methods as they emerge and determine which methods are most appropriate for which use cases. In this work, we introduce a generalizable benchmarking framework to appraise key characteristics of synthetic health data with respect to utility and privacy metrics. We apply the framework to evaluate synthetic data generation methods for electronic health records (EHRs) data from two large academic medical centers with respect to several use cases. The results illustrate that there is a utility-privacy tradeoff for sharing synthetic EHR data. The results further indicate that no method is unequivocally the best on all criteria in each use case, which makes it evident why synthetic data generation methods need to be assessed in context.

Gongbo Zhang, Qiao Jin, Denis Jered McInerney et al. · amazon-science, salesforce

Evidence-based medicine promises to improve the quality of healthcare by empowering medical decisions and practices with the best available evidence. The rapid growth of medical evidence, which can be obtained from various sources, poses a challenge in collecting, appraising, and synthesizing the evidential information. Recent advancements in generative AI, exemplified by large language models, hold promise in facilitating the arduous task. However, developing accountable, fair, and inclusive models remains a complicated undertaking. In this perspective, we discuss the trustworthiness of generative AI in the context of automated summarization of medical evidence.

Betina Idnay, Zihan Xu, William G. Adams et al.

This study reports a comprehensive environmental scan of the generative AI (GenAI) infrastructure in the national network for clinical and translational science across 36 institutions supported by the Clinical and Translational Science Award (CTSA) Program led by the National Center for Advancing Translational Sciences (NCATS) of the National Institutes of Health (NIH) at the United States. With the rapid advancement of GenAI technologies, including large language models (LLMs), healthcare institutions face unprecedented opportunities and challenges. This research explores the current status of GenAI integration, focusing on stakeholder roles, governance structures, and ethical considerations by administering a survey among leaders of health institutions (i.e., representing academic medical centers and health systems) to assess the institutional readiness and approach towards GenAI adoption. Key findings indicate a diverse range of institutional strategies, with most organizations in the experimental phase of GenAI deployment. The study highlights significant variations in governance models, with a strong preference for centralized decision-making but notable gaps in workforce training and ethical oversight. Moreover, the results underscore the need for a more coordinated approach to GenAI governance, emphasizing collaboration among senior leaders, clinicians, information technology staff, and researchers. Our analysis also reveals concerns regarding GenAI bias, data security, and stakeholder trust, which must be addressed to ensure the ethical and effective implementation of GenAI technologies. This study offers valuable insights into the challenges and opportunities of GenAI integration in healthcare, providing a roadmap for institutions aiming to leverage GenAI for improved quality of care and operational efficiency.

Rajagopal Venkatesaramani, Zhiyu Wan, Bradley A. Malin et al.

The collection and sharing of genomic data are becoming increasingly commonplace in research, clinical, and direct-to-consumer settings. The computational protocols typically adopted to protect individual privacy include sharing summary statistics, such as allele frequencies, or limiting query responses to the presence/absence of alleles of interest using web-services called Beacons. However, even such limited releases are susceptible to likelihood-ratio-based membership-inference attacks. Several approaches have been proposed to preserve privacy, which either suppress a subset of genomic variants or modify query responses for specific variants (e.g., adding noise, as in differential privacy). However, many of these approaches result in a significant utility loss, either suppressing many variants or adding a substantial amount of noise. In this paper, we introduce optimization-based approaches to explicitly trade off the utility of summary data or Beacon responses and privacy with respect to membership-inference attacks based on likelihood-ratios, combining variant suppression and modification. We consider two attack models. In the first, an attacker applies a likelihood-ratio test to make membership-inference claims. In the second model, an attacker uses a threshold that accounts for the effect of the data release on the separation in scores between individuals in the dataset and those who are not. We further introduce highly scalable approaches for approximately solving the privacy-utility tradeoff problem when information is either in the form of summary statistics or presence/absence queries. Finally, we show that the proposed approaches outperform the state of the art in both utility and privacy through an extensive evaluation with public datasets.

Jiaxin Zhang, Zhuohang Li, Kamalika Das et al.

Hallucination detection is a critical step toward understanding the trustworthiness of modern language models (LMs). To achieve this goal, we re-examine existing detection approaches based on the self-consistency of LMs and uncover two types of hallucinations resulting from 1) question-level and 2) model-level, which cannot be effectively identified through self-consistency check alone. Building upon this discovery, we propose a novel sampling-based method, i.e., semantic-aware cross-check consistency (SAC3) that expands on the principle of self-consistency checking. Our SAC3 approach incorporates additional mechanisms to detect both question-level and model-level hallucinations by leveraging advances including semantically equivalent question perturbation and cross-model response consistency checking. Through extensive and systematic empirical analysis, we demonstrate that SAC3 outperforms the state of the art in detecting both non-factual and factual statements across multiple question-answering and open-domain generation benchmarks.

Kevin H. Guo, Chao Yan, Avinash Baidya et al.

Large language models (LLMs) are known to abandon their initial stance to conform to user pushback. While prior research largely attributes this behavior to sycophancy learned during reinforcement learning from human feedback, we hypothesize that conformity is also driven by a model's epistemic uncertainty at inference time. In this paper, we introduce MUSE, a two-stage evaluation framework to disentangle the mechanisms driving LLM conformity. Specifically, MUSE maps a model's epistemic uncertainty in responding to a query against its likelihood to yield to user pushback in a subsequent turn. We demonstrate that the mechanisms driving conformity extend beyond sycophancy alone. Specifically, we characterize two distinct factors that jointly drive conformity: sycophantic conformity, where a model aligns with user pushback even with absolute certainty in its initial response, and uncertainty-driven conformity, where a model's likelihood for conformity increases alongside its uncertainty. Furthermore, we conduct ablation studies to demonstrate that both sycophantic conformity and uncertainty-driven conformity grow with 1) the LLM's perceived expertise of the user and 2) the plausibility of the user's suggestions. More broadly, MUSE informs more targeted intervention strategies by distinguishing alignment-induced sycophancy and training-corpora-driven uncertainty.

Zhuohang Li, Chao Yan, Xinmeng Zhang et al.

Deep learning continues to rapidly evolve and is now demonstrating remarkable potential for numerous medical prediction tasks. However, realizing deep learning models that generalize across healthcare organizations is challenging. This is due, in part, to the inherent siloed nature of these organizations and patient privacy requirements. To address this problem, we illustrate how split learning can enable collaborative training of deep learning models across disparate and privately maintained health datasets, while keeping the original records and model parameters private. We introduce a new privacy-preserving distributed learning framework that offers a higher level of privacy compared to conventional federated learning. We use several biomedical imaging and electronic health record (EHR) datasets to show that deep learning models trained via split learning can achieve highly similar performance to their centralized and federated counterparts while greatly improving computational efficiency and reducing privacy risks.

Chris Clifton, Bradley Malin, Anna Oganian et al.

Government agencies collect and manage a wide range of ever-growing datasets. While such data has the potential to support research and evidence-based policy making, there are concerns that the dissemination of such data could infringe upon the privacy of the individuals (or organizations) from whom such data was collected. To appraise the current state of data sharing, as well as learn about opportunities for stimulating such sharing at a faster pace, a virtual workshop was held on May 21st and 26th, 2021, sponsored by the National Science Foundation (NSF) and National Institute of Standards and Technologies (NIST), and the White House Office of Science and Technology Policy (OSTP), where a multinational collection of researchers and practitioners were brought together to discuss their experiences and learn about recently developed technologies for managing privacy while sharing data. The workshop specifically focused on challenges and successes in government data sharing at various levels. The first day focused on successful examples of new technology applied to sharing of public data, including formal privacy techniques, synthetic data, and cryptographic approaches. Day two emphasized brainstorming sessions on some of the challenges and directions to address them.

Weixin Liu, Bowen Qu, Juming Xiong et al.

Large language model (LLM) summarization systems may pass compact vector representations of private inputs to downstream retrieval, monitoring, audit, or analytic workflows. Even when source documents remain access-restricted, derived vectors may be handled under different access controls and still support sensitive-information inference, creating a residual information-disclosure risk. We study this issue in clinical discharge-summary generation as a high-stakes case study, using electronic health record (EHR)-recorded race as a controlled sensitive-label audit. We audit two artifacts that a system might retain or expose to downstream components: the final prompt-token hidden state and the mean-pooled prompt representation. Our results show that reducing recoverability of the case-study sensitive label from one exported artifact does not necessarily reduce recoverability from another. As a mitigation case study, we introduce SurfaceLoRA, an exported-vector-targeted parameter-efficient fine-tuning method that uses a gradient-reversal discriminator attached to a designated exported vector. Under a balanced five-way probing protocol, SurfaceLoRA reduces EHR-recorded race recoverability from the targeted final-token artifact toward chance while preserving summarization utility, yet recoverability remains substantially higher from untargeted pooled artifacts. These findings show that privacy auditing and mitigation should be performed on the exact vector artifact retained or exposed to downstream components.

Kevin H. Guo, Chao Yan, Avinash Baidya et al.

Medical large language model (LLM) evaluations rely on simplified, exam-style benchmarks that rarely reflect the ambiguity of real-world medical inquiries. We introduce the CLinical Evaluation of Ambiguity and Reliability (CLEAR) framework, which assesses how decision-space presentation, ambiguity, and uncertainty affect LLMs' reasoning on medical benchmarks. CLEAR systematically perturbs (1) the number of plausible answer options, (2) the presence of a ground truth or abstention option, and (3) the semantic framing of answer options. Applying CLEAR on three benchmarks evaluated across 17 LLMs reveals three notable limitations of existing evaluation methods. First, increasing the number of plausible answers degrades a model's ability to identify the correct answer and abstain against incorrect ones. Second, this lack of caution intensifies as the framing of abstention shifts from assertive rejection like "None of the Above" to uncertainty admission like "I don't know" (IDK). Notably, just including IDK in the answer space increases incorrect answer selections. Lastly, we formalize the performance gap between identifying the correct answer and abstaining from incorrect ones as the humility deficit, which worsens with model scale. Our findings reveal limitations in standard medical benchmarks and underscore that scaling alone does not resolve LLM reliability issues.

Khizar Hussain, Bradley A. Malin, Zhijun Yin et al.

As LLM-powered chatbots are increasingly deployed in mental health services, detecting hallucinations and omissions has become critical for user safety. However, state-of-the-art LLM-as-a-judge methods often fail in high-risk healthcare contexts, where subtle errors can have serious consequences. We show that leading LLM judges achieve only 52% accuracy on mental health counseling data, with some hallucination detection approaches exhibiting near-zero recall. We identify the root cause as LLMs' inability to capture nuanced linguistic and therapeutic patterns recognized by domain experts. To address this, we propose a framework that integrates human expertise with LLMs to extract interpretable, domain-informed features across five analytical dimensions: logical consistency, entity verification, factual accuracy, linguistic uncertainty, and professional appropriateness. Experiments on a public mental health dataset and a new human-annotated dataset show that traditional machine learning models trained on these features achieve 0.717 F1 on our custom dataset and 0.849 F1 on a public benchmark for hallucination detection, with 0.59-0.64 F1 for omission detection across both datasets. Our results demonstrate that combining domain expertise with automated methods yields more reliable and transparent evaluation than black-box LLM judging in high-stakes mental health applications.

Zhuohang Li, Andrew Lowy, Jing Liu et al.

In distributed learning settings, models are iteratively updated with shared gradients computed from potentially sensitive user data. While previous work has studied various privacy risks of sharing gradients, our paper aims to provide a systematic approach to analyze private information leakage from gradients. We present a unified game-based framework that encompasses a broad range of attacks including attribute, property, distributional, and user disclosures. We investigate how different uncertainties of the adversary affect their inferential power via extensive experiments on five datasets across various data modalities. Our results demonstrate the inefficacy of solely relying on data aggregation to achieve privacy against inference attacks in distributed learning. We further evaluate five types of defenses, namely, gradient pruning, signed gradient descent, adversarial perturbations, variational information bottleneck, and differential privacy, under both static and adaptive adversary settings. We provide an information-theoretic view for analyzing the effectiveness of these defenses against inference from gradients. Finally, we introduce a method for auditing attribute inference privacy, improving the empirical estimation of worst-case privacy through crafting adversarial canary records.

Victor Borza, Andrew Estornell, Ellen Wright Clayton et al.

Large participatory biomedical studies, studies that recruit individuals to join a dataset, are gaining popularity and investment, especially for analysis by modern AI methods. Because they purposively recruit participants, these studies are uniquely able to address a lack of historical representation, an issue that has affected many biomedical datasets. In this work, we define representativeness as the similarity to a target population distribution of a set of attributes and our goal is to mirror the U.S. population across distributions of age, gender, race, and ethnicity. Many participatory studies recruit at several institutions, so we introduce a computational approach to adaptively allocate recruitment resources among sites to improve representativeness. In simulated recruitment of 10,000-participant cohorts from medical centers in the STAR Clinical Research Network, we show that our approach yields a more representative cohort than existing baselines. Thus, we highlight the value of computational modeling in guiding recruitment efforts.

Daniela A. Wiepert, Bradley A. Malin, Joseph R. Duffy et al.

Large, curated datasets are required to leverage speech-based tools in healthcare. These are costly to produce, resulting in increased interest in data sharing. As speech can potentially identify speakers (i.e., voiceprints), sharing recordings raises privacy concerns. We examine the re-identification risk for speech recordings, without reference to demographic or metadata, using a state-of-the-art speaker recognition system. We demonstrate that the risk is inversely related to the number of comparisons an adversary must consider, i.e., the search space. Risk is high for a small search space but drops as the search space grows ($precision >0.85$ for $<1*10^{6}$ comparisons, $precision <0.5$ for $>3*10^{6}$ comparisons). Next, we show that the nature of a speech recording influences re-identification risk, with non-connected speech (e.g., vowel prolongation) being harder to identify. Our findings suggest that speaker recognition systems can be used to re-identify participants in specific circumstances, but in practice, the re-identification risk appears low.

Steve Nyemba, Chao Yan, Ziqi Zhang et al.

Artificial intelligence, and particularly machine learning (ML), is increasingly developed and deployed to support healthcare in a variety of settings. However, clinical decision support (CDS) technologies based on ML need to be portable if they are to be adopted on a broad scale. In this respect, models developed at one institution should be reusable at another. Yet there are numerous examples of portability failure, particularly due to naive application of ML models. Portability failure can lead to suboptimal care and medical errors, which ultimately could prevent the adoption of ML-based CDS in practice. One specific healthcare challenge that could benefit from enhanced portability is the prediction of 30-day readmission risk. Research to date has shown that deep learning models can be effective at modeling such risk. In this work, we investigate the practicality of model portability through a cross-site evaluation of readmission prediction models. To do so, we apply a recurrent neural network, augmented with self-attention and blended with expert features, to build readmission prediction models for two independent large scale claims datasets. We further present a novel transfer learning technique that adapts the well-known method of born-again network (BAN) training. Our experiments show that direct application of ML models trained at one institution and tested at another institution perform worse than models trained and tested at the same institution. We further show that the transfer learning approach based on the BAN produces models that are better than those trained on just a single institution's data. Notably, this improvement is consistent across both sites and occurs after a single retraining, which illustrates the potential for a cheap and general model transfer mechanism of readmission risk prediction.

Jiaxin Zhang, Wendi Cui, Zhuohang Li et al.

While Large Language Models (LLMs) show remarkable capabilities, their unreliability remains a critical barrier to deployment in high-stakes domains. This survey charts a functional evolution in addressing this challenge: the evolution of uncertainty from a passive diagnostic metric to an active control signal guiding real-time model behavior. We demonstrate how uncertainty is leveraged as an active control signal across three frontiers: in \textbf{advanced reasoning} to optimize computation and trigger self-correction; in \textbf{autonomous agents} to govern metacognitive decisions about tool use and information seeking; and in \textbf{reinforcement learning} to mitigate reward hacking and enable self-improvement via intrinsic rewards. By grounding these advancements in emerging theoretical frameworks like Bayesian methods and Conformal Prediction, we provide a unified perspective on this transformative trend. This survey provides a comprehensive overview, critical analysis, and practical design patterns, arguing that mastering the new trend of uncertainty is essential for building the next generation of scalable, reliable, and trustworthy AI.

Weixin Liu, Congning Ni, Qingyuan Song et al.

Brief Hospital Course (BHC) narratives must be clinically useful yet faithful to fragmented EHR evidence. LLM-based clinical summarizers still introduce unsupported statements, and alignment can encourage omissions ("say-less" degeneration). We introduce VERI-DPO, which uses claim verification to mine preferences and distill them into the summarizer with Direct Preference Optimization (DPO). On MIMIC-III-Ext-VeriFact-BHC (100 ICU patients; patient-level splits), we train a retrieval-augmented verifier to label claim-evidence pairs as Supported, Not Supported, or Not Addressed via a single-token format. The verifier scores sentence-level claims from sampled BHC candidates and aggregates margins into a coverage-aware utility to mine length-controlled, contradiction-anchored preference pairs. On held-out patients, verifier-mined preferences separate candidates by contradiction density, and VERI-DPO reduces Not Supported claim rates from 10.7% to 1.9% (local verifier judge) and from 11.6% to 6.4% (GPT-4o judge), while improving validity from 76.7% to 82.5% and maintaining informative length.

Kevin H. Guo, Chao Yan, Avinash Baidya et al.

Patients and clinicians are increasingly using chatbots powered by large language models (LLMs) for healthcare inquiries. While state-of-the-art LLMs exhibit high performance on static diagnostic reasoning benchmarks, their efficacy across multi-turn conversations, which better reflect real-world usage, has been understudied. In this paper, we evaluate 17 LLMs across three clinical datasets to investigate how partitioning the decision-space into multiple simpler turns of conversation influences their diagnostic reasoning. Specifically, we develop a "stick-or-switch" evaluation framework to measure model conviction (i.e., defending a correct diagnosis or safe abstention against incorrect suggestions) and flexibility (i.e., recognizing a correct suggestion when it is introduced) across conversations. Our experiments reveal the conversation tax, where multi-turn interactions consistently degrade performance when compared to single-shot baselines. Notably, models frequently abandon initial correct diagnoses and safe abstentions to align with incorrect user suggestions. Additionally, several models exhibit blind switching, failing to distinguish between signal and incorrect suggestions.

Natalia Espinosa-Dice, Nicholas J. Jackson, Chao Yan et al.

Synthetic data generation (SDG) is a promising approach for enabling data sharing in biomedical studies while preserving patient privacy. Yet, state-of-the-art generative models often require large datasets and complex training procedures, limiting their applicability in small-sample settings common in biomedical research. This study aims to develop a more principled and efficient approach to SDG and evaluate its efficacy for biomedical applications. In this work, we reframe SDG as a reinforcement learning (RL) problem and introduce RLSyn, a novel framework that models the data generator as a stochastic policy over patient records and optimizes it using Proximal Policy Optimization with discriminator-derived rewards. We evaluate RLSyn on two biomedical datasets--AI-READI and MIMIC-IV--and benchmark it against state-of-the-art generative adversarial networks (GANs) and diffusion-based methods across extensive privacy, utility, and fidelity evaluations. On MIMIC-IV, RLSyn achieves predictive utility comparable to diffusion models (S2R AUC 0.902 vs 0.906 respectively) while slightly outperforming them in fidelity (NMI 0.001 vs. 0.003; DWD 2.073 vs. 2.797) and achieving comparable, low privacy risk (~0.50 membership inference risk AUC). On the smaller AI-READI dataset, RLSyn again matches diffusion-based utility (S2R AUC 0.873 vs. 0.871), while achieving higher fidelity (NMI 0.001 vs. 0.002; DWD 13.352 vs. 16.441) and significantly lower vulnerability to membership inference attacks (AUC 0.544 vs. 0.601). Both RLSyn and diffusion-based models substantially outperform GANs across utility and fidelity on both datasets. Our results suggest that reinforcement learning provides a principled and effective approach for synthetic biomedical data generation, particularly in data-scarce regimes.

Weixin Liu, Juming Xiong, Congning Ni et al.

Many time-series forecasts depend not only on prior observations but also on actions specified during the forecast period. In intensive care units (ICUs), future vital signs and laboratory values are influenced by treatments such as vasopressors. However, models that predict the full future sequence all at once make little use of these treatments, whereas autoregressive models can accumulate errors. We introduce DRIFT, a hybrid framework in which a direct model produces the primary forecast and a recursive, action-conditioned model contributes constrained corrections. We evaluate DRIFT on 6,046 admissions from MIMIC-IV and 8,345 admissions from eICU-CRD. Averaged across the 8-, 24-, and 48-hour forecast endpoints, DRIFT reduces mean absolute error for mean arterial pressure (MAP) by 0.673% relative to an action-conditioned Temporal Fusion Transformer (TFT-action) on MIMIC-IV and achieves the lowest corresponding error among the compared models on eICU-CRD. Although the overall accuracy improvement is modest, a MIMIC-IV audit restricted to windows in which the supplied treatment sequence was altered showed that DRIFT achieved lower observed-target MAP error than TFT-action at 8 and 24 hours. Treatment-sequence alteration increased DRIFT's MAP error by 0.21-0.26 mmHg more than it increased TFT-action's error, with prediction changes occurring primarily after the supplied paths diverged. In a separate robustness experiment, the MAP advantage persisted under three shared checkpoint-selection rules emphasizing overall endpoint error, MAP error, or both equally.

Wendi Cui, Zhuohang Li, Hao Sun et al.

Designing optimal prompts for Large Language Models (LLMs) is a complicated and resource-intensive task, often requiring substantial human expertise and effort. Existing approaches typically separate the optimization of prompt instructions and in-context learning examples, leading to incohesive prompts that are defined and represented by suboptimal task performance. To overcome these challenges, we propose a novel Cohesive In-Context Prompt Optimization framework that refines both prompt instructions and examples. However, formulating such an optimization in the discrete and high-dimensional space of natural language poses significant challenges in both convergence and computational efficiency. To address these issues, we introduce SEE, a scalable and efficient prompt optimization framework that adopts metaheuristic optimization principles and strategically balances exploration and exploitation to enhance optimization performance and achieve efficient convergence. SEE features a quad-phased design that alternates between global traversal (exploration) and local optimization (exploitation) and adaptively chooses LLM operators during the optimization process. We have conducted a comprehensive evaluation across 35 benchmark tasks, and SEE significantly outperforms state-of-the-art baseline methods by a large margin, achieving an average performance gain of 13.94 while reducing computational costs by 58.67.

Lisa Pilgram, Fida K. Dankar, Jorg Drechsler et al.

Synthetic data generation is one approach for sharing individual-level data. However, to meet legislative requirements, it is necessary to demonstrate that the individuals' privacy is adequately protected. There is no consolidated standard for measuring privacy in synthetic data. Through an expert panel and consensus process, we developed a framework for evaluating privacy in synthetic data. Our findings indicate that current similarity metrics fail to measure identity disclosure, and their use is discouraged. For differentially private synthetic data, a privacy budget other than close to zero was not considered interpretable. There was consensus on the importance of membership and attribute disclosure, both of which involve inferring personal information about an individual without necessarily revealing their identity. The resultant framework provides precise recommendations for metrics that address these types of disclosures effectively. Our findings further present specific opportunities for future research that can help with widespread adoption of synthetic data.

Wendi Cui, Zhuohang Li, Hao Sun et al.

Recent advances in Large Language Models have led to remarkable achievements across a variety of Natural Language Processing tasks, making prompt engineering increasingly central to guiding model outputs. While manual methods can be effective, they typically rely on intuition and do not automatically refine prompts over time. In contrast, automatic prompt optimization employing heuristic-based search algorithms can systematically explore and improve prompts with minimal human oversight. This survey proposes a comprehensive taxonomy of these methods, categorizing them by where optimization occurs, what is optimized, what criteria drive the optimization, which operators generate new prompts, and which iterative search algorithms are applied. We further highlight specialized datasets and tools that support and accelerate automated prompt refinement. We conclude by discussing key open challenges pointing toward future opportunities for more robust and versatile LLM applications.

Wendi Cui, Jiaxin Zhang, Zhuohang Li et al.

Evaluating the quality and variability of text generated by Large Language Models (LLMs) poses a significant, yet unresolved research challenge. Traditional evaluation methods, such as ROUGE and BERTScore, which measure token similarity, often fail to capture the holistic semantic equivalence. This results in a low correlation with human judgments and intuition, which is especially problematic in high-stakes applications like healthcare and finance where reliability, safety, and robust decision-making are highly critical. This work proposes DCR, an automated framework for evaluating and improving the consistency of LLM-generated texts using a divide-conquer-reasoning approach. Unlike existing LLM-based evaluators that operate at the paragraph level, our method employs a divide-and-conquer evaluator (DCE) that breaks down the paragraph-to-paragraph comparison between two generated responses into individual sentence-to-paragraph comparisons, each evaluated based on predefined criteria. To facilitate this approach, we introduce an automatic metric converter (AMC) that translates the output from DCE into an interpretable numeric score. Beyond the consistency evaluation, we further present a reason-assisted improver (RAI) that leverages the analytical reasons with explanations identified by DCE to generate new responses aimed at reducing these inconsistencies. Through comprehensive and systematic empirical analysis, we show that our approach outperforms state-of-the-art methods by a large margin (e.g., +19.3% and +24.3% on the SummEval dataset) in evaluating the consistency of LLM generation across multiple benchmarks in semantic, factual, and summarization consistency tasks. Our approach also substantially reduces nearly 90% of output inconsistencies, showing promise for effective hallucination mitigation.

Yan Zhou, Bradley Malin, Murat Kantarcioglu

Privacy-preserving data publication, including synthetic data sharing, often experiences trade-offs between privacy and utility. Synthetic data is generally more effective than data anonymization in balancing this trade-off, however, not without its own challenges. Synthetic data produced by generative models trained on source data may inadvertently reveal information about outliers. Techniques specifically designed for preserving privacy, such as introducing noise to satisfy differential privacy, often incur unpredictable and significant losses in utility. In this work we show that, with the right mechanism of synthetic data generation, we can achieve strong privacy protection without significant utility loss. Synthetic data generators producing contracting data patterns, such as Synthetic Minority Over-sampling Technique (SMOTE), can enhance a differentially private data generator, leveraging the strengths of both. We prove in theory and through empirical demonstration that this SMOTE-DP technique can produce synthetic data that not only ensures robust privacy protection but maintains utility in downstream learning tasks.

Jiaxin Zhang, Zhuohang Li, Wendi Cui et al.

Large language models (LLMs) have demonstrated remarkable performance, yet their diverse strengths and weaknesses prevent any single LLM from achieving dominance across all tasks. Ensembling multiple LLMs is a promising approach to generate reliable responses but conventional ensembling frameworks suffer from high computational overheads. This work introduces Scalable Consistency Ensemble (SCE), an efficient framework for ensembling LLMs by prompting consistent outputs. The SCE framework systematically evaluates and integrates outputs to produce a cohesive result through two core components: SCE-CHECK, a mechanism that gauges the consistency between response pairs via semantic equivalence; and SCE-FUSION, which adeptly merges the highest-ranked consistent responses from SCE-CHECK, to optimize collective strengths and mitigating potential weaknesses. To improve the scalability with multiple inference queries, we further propose ``{You Only Prompt Once}'' (YOPO), a novel technique that reduces the inference complexity of pairwise comparison from quadratic to constant time. We perform extensive empirical evaluations on diverse benchmark datasets to demonstrate \methodName's effectiveness. Notably, the \saccheckcomponent outperforms conventional baselines with enhanced performance and a significant reduction in computational overhead.

Yanfan Zhu, Issac Lyngaas, Murali Gopalakrishnan Meena et al.

Recent advancements in AI models are structured to retain user interactions, which could inadvertently include sensitive healthcare data. In the healthcare field, particularly when radiologists use AI-driven diagnostic tools hosted on online platforms, there is a risk that medical imaging data may be repurposed for future AI training without explicit consent, spotlighting critical privacy and intellectual property concerns around healthcare data usage. Addressing these privacy challenges, a novel approach known as Unlearnable Examples (UEs) has been introduced, aiming to make data unlearnable to deep learning models. A prominent method within this area, called Unlearnable Clustering (UC), has shown improved UE performance with larger batch sizes but was previously limited by computational resources. To push the boundaries of UE performance with theoretically unlimited resources, we scaled up UC learning across various datasets using Distributed Data Parallel (DDP) training on the Summit supercomputer. Our goal was to examine UE efficacy at high-performance computing (HPC) levels to prevent unauthorized learning and enhance data security, particularly exploring the impact of batch size on UE's unlearnability. Utilizing the robust computational capabilities of the Summit, extensive experiments were conducted on diverse datasets such as Pets, MedMNist, Flowers, and Flowers102. Our findings reveal that both overly large and overly small batch sizes can lead to performance instability and affect accuracy. However, the relationship between batch size and unlearnability varied across datasets, highlighting the necessity for tailored batch size strategies to achieve optimal data protection. Our results underscore the critical role of selecting appropriate batch sizes based on the specific characteristics of each dataset to prevent learning and ensure data security in deep learning applications.

Congning Ni, Sarvech Qadir, Bryan Steitz et al.

Mental health concerns are often expressed outside clinical settings, including in high-distress help seeking, where safety-critical guidance may be needed. Consumer health informatics systems increasingly incorporate large language models (LLMs) for mental health question answering, yet many evaluations underrepresent narrative, high-distress inquiries. We introduce UTCO (User, Topic, Context, Tone), a prompt construction framework that represents an inquiry as four controllable elements for systematic stress testing. Using 2,075 UTCO-generated prompts, we evaluated Llama 3.3 and annotated hallucinations (fabricated or incorrect clinical content) and omissions (missing clinically necessary or safety-critical guidance). Hallucinations occurred in 6.5% of responses and omissions in 13.2%, with omissions concentrated in crisis and suicidal ideation prompts. Across regression, element-specific matching, and similarity-matched comparisons, failures were most consistently associated with context and tone, while user-background indicators showed no systematic differences after balancing. These findings support evaluating omissions as a primary safety outcome and moving beyond static benchmark question sets.

Amir Asiaee, Chao Yan, Zachary B. Abrams et al.

Differential privacy (DP) provides a mathematical guarantee limiting what an adversary can learn about any individual from released data. However, achieving this protection typically requires adding noise, and noise can accumulate when many statistics are measured. Existing DP synthetic data methods treat all features symmetrically, spreading noise uniformly even when the data will serve a specific prediction task. We develop a prediction-centric approach operating in three regimes depending on available structural knowledge. In the causal regime, when the causal parents of $Y$ are known and distribution shift is expected, we target the parents for robustness. In the graphical regime, when a Bayesian network structure is available and the distribution is stable, the Markov blanket of $Y$ provides a sufficient feature set for optimal prediction. In the predictive regime, when no structural knowledge exists, we select features via differentially private methods without claiming to recover causal or graphical structure. We formalize this as PRISM, a mechanism that (i) identifies a predictive feature subset according to the appropriate regime, (ii) constructs targeted summary statistics, (iii) allocates budget to minimize an upper bound on prediction error, and (iv) synthesizes data via graphical-model inference. We prove end-to-end privacy guarantees and risk bounds. Empirically, task-aware allocation improves prediction accuracy compared to generic synthesizers. Under distribution shift, targeting causal parents achieves AUC $\approx 0.73$ while correlation-based selection collapses to chance ($\approx 0.49$).

Amir Asiaee, Chao Yan, Zachary B. Abrams et al.

When synthetic data is released, some individuals are harder to protect than others. A patient with a rare disease combination or a transaction with unusual characteristics stands out from the crowd. Differential privacy provides worst-case guarantees, but empirical attacks -- particularly membership inference -- succeed far more often against such outliers, especially under moderate privacy budgets and with auxiliary information. This paper introduces risk-equalized DP synthesis, a framework that prioritizes protection for high-risk records by reducing their influence on the learned generator. The mechanism operates in two stages: first, a small privacy budget estimates each record's "outlierness"; second, a DP learning procedure weights each record inversely to its risk score. Under Gaussian mechanisms, a record's privacy loss is proportional to its influence on the output -- so deliberately shrinking outliers' contributions yields tighter per-instance privacy bounds for precisely those records that need them most. We prove end-to-end DP guarantees via composition and derive closed-form per-record bounds for the synthesis stage (the scoring stage adds a uniform per-record term). Experiments on simulated data with controlled outlier injection show that risk-weighting substantially reduces membership inference success against high-outlierness records; ablations confirm that targeting -- not random downweighting -- drives the improvement. On real-world benchmarks (Breast Cancer, Adult, German Credit), gains are dataset-dependent, highlighting the interplay between scorer quality and synthesis pipeline.

Martin C. Were, Ang Li, Bradley A. Malin et al.

The role and use of race within health-related artificial intelligence and machine learning (AI/ML) models has sparked increasing attention and controversy. Despite the complexity and breadth of related issues, a robust and holistic framework to guide stakeholders in their examination and resolution remains lacking. This perspective provides a broad-based, systematic, and cross-cutting landscape analysis of race-related challenges, structured around the AI/ML lifecycle and framed through "points to consider" to support inquiry and decision-making.

Xiaoge Zhang, Tao Wang, Chao Yan et al.

Ensuring trustworthiness is fundamental to the development of artificial intelligence (AI) that is considered societally responsible, particularly in cancer diagnostics, where a misdiagnosis can have dire consequences. Current digital pathology AI models lack systematic solutions to address trustworthiness concerns arising from model limitations and data discrepancies between model deployment and development environments. To address this issue, we developed TRUECAM, a framework designed to ensure both data and model trustworthiness in non-small cell lung cancer subtyping with whole-slide images. TRUECAM integrates 1) a spectral-normalized neural Gaussian process for identifying out-of-scope inputs and 2) an ambiguity-guided elimination of tiles to filter out highly ambiguous regions, addressing data trustworthiness, as well as 3) conformal prediction to ensure controlled error rates. We systematically evaluated the framework across multiple large-scale cancer datasets, leveraging both task-specific and foundation models, illustrate that an AI model wrapped with TRUECAM significantly outperforms models that lack such guidance, in terms of classification accuracy, robustness, interpretability, and data efficiency, while also achieving improvements in fairness. These findings highlight TRUECAM as a versatile wrapper framework for digital pathology AI models with diverse architectural designs, promoting their responsible and effective applications in real-world settings.

Congning Ni, Qingxia Chen, Lijun Song et al.

Informal caregivers (e.g.,family members or friends) of people living with Alzheimers Disease and Related Dementias (ADRD) face substantial challenges and often seek informational or emotional support through online communities. Understanding the factors that drive engagement within these platforms is crucial, as it can enhance their long-term value for caregivers by ensuring that these communities effectively meet their needs. This study investigated the user interaction dynamics within two large, popular ADRD communities, TalkingPoint and ALZConnected, focusing on topic initiator engagement, initial post content, and the linguistic patterns of comments at the thread level. Using analytical methods such as propensity score matching, topic modeling, and predictive modeling, we found that active topic initiator engagement drives higher comment volumes, and reciprocal replies from topic initiators encourage further commentor engagement at the community level. Practical caregiving topics prompt more re-engagement of topic initiators, while emotional support topics attract more comments from other commentors. Additionally, the linguistic complexity and emotional tone of a comment influence its likelihood of receiving replies from topic initiators. These findings highlight the importance of fostering active and reciprocal engagement and providing effective strategies to enhance sustainability in ADRD caregiving and broader health-related online communities.

Victor Borza, Andrew Estornell, Chien-Ju Ho et al.

Our society collects data on people for a wide range of applications, from building a census for policy evaluation to running meaningful clinical trials. To collect data, we typically sample individuals with the goal of accurately representing a population of interest. However, current sampling processes often collect data opportunistically from data sources, which can lead to datasets that are biased and not representative, i.e., the collected dataset does not accurately reflect the distribution of demographics of the true population. This is a concern because subgroups within the population can be under- or over-represented in a dataset, which may harm generalizability and lead to an unequal distribution of benefits and harms from downstream tasks that use such datasets (e.g., algorithmic bias in medical decision-making algorithms). In this paper, we assess the relationship between dataset representativeness and group-fairness of classifiers trained on that dataset. We demonstrate that there is a natural tension between dataset representativeness and classifier fairness; empirically we observe that training datasets with better representativeness can frequently result in classifiers with higher rates of unfairness. We provide some intuition as to why this occurs via a set of theoretical results in the case of univariate classifiers. We also find that over-sampling underrepresented groups can result in classifiers which exhibit greater bias to those groups. Lastly, we observe that fairness-aware sampling strategies (i.e., those which are specifically designed to select data with high downstream fairness) will often over-sample members of majority groups. These results demonstrate that the relationship between dataset representativeness and downstream classifier fairness is complex; balancing these two quantities requires special care from both model- and dataset-designers.

Rajagopal Venkatesaramani, Zhiyu Wan, Bradley A. Malin et al.

Large genomic datasets are now created through numerous activities, including recreational genealogical investigations, biomedical research, and clinical care. At the same time, genomic data has become valuable for reuse beyond their initial point of collection, but privacy concerns often hinder access. Over the past several years, Beacon services have emerged to broaden accessibility to such data. These services enable users to query for the presence of a particular minor allele in a private dataset, information that can help care providers determine if genomic variation is spurious or has some known clinical indication. However, various studies have shown that even this limited access model can leak if individuals are members in the underlying dataset. Several approaches for mitigating this vulnerability have been proposed, but they are limited in that they 1) typically rely on heuristics and 2) offer probabilistic privacy guarantees, but neglect utility. In this paper, we present a novel algorithmic framework to ensure privacy in a Beacon service setting with a minimal number of query response flips (e.g., changing a positive response to a negative). Specifically, we represent this problem as combinatorial optimization in both the batch setting (where queries arrive all at once), as well as the online setting (where queries arrive sequentially). The former setting has been the primary focus in prior literature, whereas real Beacons allow sequential queries, motivating the latter investigation. We present principled algorithms in this framework with both privacy and, in some cases, worst-case utility guarantees. Moreover, through an extensive experimental evaluation, we show that the proposed approaches significantly outperform the state of the art in terms of privacy and utility.

J. Thomas Brown, Chao Yan, Weiyi Xia et al.

Supporting public health research and the public's situational awareness during a pandemic requires continuous dissemination of infectious disease surveillance data. Legislation, such as the Health Insurance Portability and Accountability Act of 1996 (HIPAA) and recent state-level regulations, permits sharing de-identified person-level data; however, current de-identification approaches are limited. namely, they are inefficient, relying on retrospective disclosure risk assessments, and do not flex with changes in infection rates or population demographics over time. In this paper, we introduce a framework to dynamically adapt de-identification for near-real time sharing of person-level surveillance data. The framework leverages a simulation mechanism, capable of application at any geographic level, to forecast the re-identification risk of sharing the data under a wide range of generalization policies. The estimates inform weekly, prospective policy selection to maintain the proportion of records corresponding to a group size less than 11 (PK11) at or below 0.1. Fixing the policy at the start of each week facilitates timely dataset updates and supports sharing granular date information. We use August 2020 through October 2021 case data from Johns Hopkins University and the Centers for Disease Control and Prevention to demonstrate the framework's effectiveness in maintaining the PK!1 threshold of 0.01. When sharing COVID-19 county-level case data across all US counties, the framework's approach meets the threshold for 96.2% of daily data releases, while a policy based on current de-identification techniques meets the threshold for 32.3%. Periodically adapting the data publication policies preserves privacy while enhancing public health utility through timely updates and sharing epidemiologically critical features.

Prithwish Chakraborty, James Codella, Piyush Madan et al.

Deep learning architectures have an extremely high-capacity for modeling complex data in a wide variety of domains. However, these architectures have been limited in their ability to support complex prediction problems using insurance claims data, such as readmission at 30 days, mainly due to data sparsity issue. Consequently, classical machine learning methods, especially those that embed domain knowledge in handcrafted features, are often on par with, and sometimes outperform, deep learning approaches. In this paper, we illustrate how the potential of deep learning can be achieved by blending domain knowledge within deep learning architectures to predict adverse events at hospital discharge, including readmissions. More specifically, we introduce a learning architecture that fuses a representation of patient data computed by a self-attention based recurrent neural network, with clinically relevant features. We conduct extensive experiments on a large claims dataset and show that the blended method outperforms the standard machine learning approaches.

Rajagopal Venkatesaramani, Bradley A. Malin, Yevgeniy Vorobeychik

DNA sequencing is becoming increasingly commonplace, both in medical and direct-to-consumer settings. To promote discovery, collected genomic data is often de-identified and shared, either in public repositories, such as OpenSNP, or with researchers through access-controlled repositories. However, recent studies have suggested that genomic data can be effectively matched to high-resolution three-dimensional face images, which raises a concern that the increasingly ubiquitous public face images can be linked to shared genomic data, thereby re-identifying individuals in the genomic data. While these investigations illustrate the possibility of such an attack, they assume that those performing the linkage have access to extremely well-curated data. Given that this is unlikely to be the case in practice, it calls into question the pragmatic nature of the attack. As such, we systematically study this re-identification risk from two perspectives: first, we investigate how successful such linkage attacks can be when real face images are used, and second, we consider how we can empower individuals to have better control over the associated re-identification risk. We observe that the true risk of re-identification is likely substantially smaller for most individuals than prior literature suggests. In addition, we demonstrate that the addition of a small amount of carefully crafted noise to images can enable a controlled trade-off between re-identification success and the quality of shared images, with risk typically significantly lowered even with noise that is imperceptible to humans.

Siddharth Biswal, Soumya Ghosh, Jon Duke et al.

Researchers require timely access to real-world longitudinal electronic health records (EHR) to develop, test, validate, and implement machine learning solutions that improve the quality and efficiency of healthcare. In contrast, health systems value deeply patient privacy and data security. De-identified EHRs do not adequately address the needs of health systems, as de-identified data are susceptible to re-identification and its volume is also limited. Synthetic EHRs offer a potential solution. In this paper, we propose EHR Variational Autoencoder (EVA) for synthesizing sequences of discrete EHR encounters (e.g., clinical visits) and encounter features (e.g., diagnoses, medications, procedures). We illustrate that EVA can produce realistic EHR sequences, account for individual differences among patients, and can be conditioned on specific disease conditions, thus enabling disease-specific studies. We design efficient, accurate inference algorithms by combining stochastic gradient Markov Chain Monte Carlo with amortized variational inference. We assess the utility of the methods on large real-world EHR repositories containing over 250, 000 patients. Our experiments, which include user studies with knowledgeable clinicians, indicate the generated EHR sequences are realistic. We confirmed the performance of predictive models trained on the synthetic data are similar with those trained on real EHRs. Additionally, our findings indicate that augmenting real data with synthetic EHRs results in the best predictive performance - improving the best baseline by as much as 8% in top-20 recall.

Aref Asvadishirehjini, Murat Kantarcioglu, Bradley Malin

Machine learning models based on Deep Neural Networks (DNNs) are increasingly deployed in a wide range of applications ranging from self-driving cars to COVID-19 treatment discovery. To support the computational power necessary to learn a DNN, cloud environments with dedicated hardware support have emerged as critical infrastructure. However, there are many integrity challenges associated with outsourcing computation. Various approaches have been developed to address these challenges, building on trusted execution environments (TEE). Yet, no existing approach scales up to support realistic integrity-preserving DNN model training for heavy workloads (deep architectures and millions of training examples) without sustaining a significant performance hit. To mitigate the time gap between pure TEE (full integrity) and pure GPU (no integrity), we combine random verification of selected computation steps with systematic adjustments of DNN hyper-parameters (e.g., a narrow gradient clipping range), hence limiting the attacker's ability to shift the model parameters significantly provided that the step is not selected for verification during its training phase. Experimental results show the new approach achieves 2X to 20X performance improvement over pure TEE based solution while guaranteeing a very high probability of integrity (e.g., 0.999) with respect to state-of-the-art DNN backdoor attacks.

Chao Yan, Ziqi Zhang, Steve Nyemba et al.

Sharing electronic health records (EHRs) on a large scale may lead to privacy intrusions. Recent research has shown that risks may be mitigated by simulating EHRs through generative adversarial network (GAN) frameworks. Yet the methods developed to date are limited because they 1) focus on generating data of a single type (e.g., diagnosis codes), neglecting other data types (e.g., demographics, procedures or vital signs) and 2) do not represent constraints between features. In this paper, we introduce a method to simulate EHRs composed of multiple data types by 1) refining the GAN model, 2) accounting for feature constraints, and 3) incorporating key utility measures for such generation tasks. Our analysis with over $770,000$ EHRs from Vanderbilt University Medical Center demonstrates that the new model achieves higher performance in terms of retaining basic statistics, cross-feature correlations, latent structural properties, feature constraints and associated patterns from real data, without sacrificing privacy.

Mustafa Safa Ozdayi, Murat Kantarcioglu, Bradley Malin

Blockchain has emerged as a decentralized and distributed framework that enables tamper-resilience and, thus, practical immutability for stored data. This immutability property is important in scenarios where auditability is desired, such as in maintaining access logs for sensitive healthcare and biomedical data.However, the underlying data structure of blockchain, by default, does not provide capabilities to efficiently query the stored data. In this investigation, we show that it is possible to efficiently run complex audit queries over the access log data stored on blockchains by using additional key-value stores. This paper specifically reports on the approach we designed for the blockchain track of iDASH Privacy & Security Workshop 2018 competition.Particularly, we implemented our solution and compared its loading and query-response performance with SQLite, a commonly used relational database, using the data provided by the iDASH 2018 organizers. Depending on the query type and the data size, the run time difference between blockchain based query-response and SQLite based query-response ranged from 0.2 seconds to 6 seconds. A deeper inspection revealed that range queries were the bottleneck of our solution which, nevertheless, scales up linearly. Concretely, this investigation demonstrates that blockchain-based systems can provide reasonable query-response times to complex queries even if they only use simple key-value stores to manage their data. Consequently, we show that blockchains may be useful for maintaining data with auditability and immutability requirements across multiple sites.

Chao Yan, Haifeng Xu, Yevgeniy Vorobeychik et al.

Routine operational use of sensitive data is often governed by law and regulation. For instance, in the medical domain, there are various statues at the state and federal level that dictate who is permitted to work with patients' records and under what conditions. To screen for potential privacy breaches, logging systems are usually deployed to trigger alerts whenever suspicious access is detected. However, such mechanisms are often inefficient because 1) the vast majority of triggered alerts are false positives, 2) small budgets make it unlikely that a real attack will be detected, and 3) attackers can behave strategically, such that traditional auditing mechanisms cannot easily catch them. To improve efficiency, information systems may invoke signaling, so that whenever a suspicious access request occurs, the system can, in real time, warn the user that the access may be audited. Then, at the close of a finite period, a selected subset of suspicious accesses are audited. This gives rise to an online problem in which one needs to determine 1) whether a warning should be triggered and 2) the likelihood that the data request event will be audited. In this paper, we formalize this auditing problem as a Signaling Audit Game (SAG), in which we model the interactions between an auditor and an attacker in the context of signaling and the usability cost is represented as a factor of the auditor's payoff. We study the properties of its Stackelberg equilibria and develop a scalable approach to compute its solution. We show that a strategic presentation of warnings adds value in that SAGs realize significantly higher utility for the auditor than systems without signaling. We illustrate the value of the proposed auditing model and the consistency of its advantages over existing baseline methods.

Jette Henderson, Bradley A. Malin, Joyce C. Ho et al.

It has been recently shown that sparse, nonnegative tensor factorization of multi-modal electronic health record data is a promising approach to high-throughput computational phenotyping. However, such approaches typically do not leverage available domain knowledge while extracting the phenotypes; hence, some of the suggested phenotypes may not map well to clinical concepts or may be very similar to other suggested phenotypes. To address these issues, we present a novel, automatic approach called PIVETed-Granite that mines existing biomedical literature (PubMed) to obtain cannot-link constraints that are then used as side-information during a tensor-factorization based computational phenotyping process. The resulting improvements are clearly observed in experiments using a large dataset from VUMC to identify phenotypes for hypertensive patients.

Chao Yan, Bo Li, Yevgeniy Vorobeychik et al.

For enhancing the privacy protections of databases, where the increasing amount of detailed personal data is stored and processed, multiple mechanisms have been developed, such as audit logging and alert triggers, which notify administrators about suspicious activities; however, the two main limitations in common are: 1) the volume of such alerts is often substantially greater than the capabilities of resource-constrained organizations, and 2) strategic attackers may disguise their actions or carefully choosing which records they touch, making incompetent the statistical detection models. For solving them, we introduce a novel approach to database auditing that explicitly accounts for adversarial behavior by 1) prioritizing the order in which types of alerts are investigated and 2) providing an upper bound on how much resource to allocate for each type. We model the interaction between a database auditor and potential attackers as a Stackelberg game in which the auditor chooses an auditing policy and attackers choose which records to target. A corresponding approach combining linear programming, column generation, and heuristic search is proposed to derive an auditing policy. For testing the policy-searching performance, a publicly available credit card application dataset are adopted, on which it shows that our methods produce high-quality mixed strategies as database audit policies, and our general approach significantly outperforms non-game-theoretic baselines.

Alexandros Mittos, Bradley Malin, Emiliano De Cristofaro

Rapid advances in human genomics are enabling researchers to gain a better understanding of the role of the genome in our health and well-being, stimulating hope for more effective and cost efficient healthcare. However, this also prompts a number of security and privacy concerns stemming from the distinctive characteristics of genomic data. To address them, a new research community has emerged and produced a large number of publications and initiatives. In this paper, we rely on a structured methodology to contextualize and provide a critical analysis of the current knowledge on privacy-enhancing technologies used for testing, storing, and sharing genomic data, using a representative sample of the work published in the past decade. We identify and discuss limitations, technical challenges, and issues faced by the community, focusing in particular on those that are inherently tied to the nature of the problem and are harder for the community alone to address. Finally, we report on the importance and difficulty of the identified challenges based on an online survey of genome data privacy experts

Edward Choi, Siddharth Biswal, Bradley Malin et al.

Access to electronic health record (EHR) data has motivated computational advances in medical research. However, various concerns, particularly over privacy, can limit access to and collaborative use of EHR data. Sharing synthetic EHR data could mitigate risk. In this paper, we propose a new approach, medical Generative Adversarial Network (medGAN), to generate realistic synthetic patient records. Based on input real patient records, medGAN can generate high-dimensional discrete variables (e.g., binary and count features) via a combination of an autoencoder and generative adversarial networks. We also propose minibatch averaging to efficiently avoid mode collapse, and increase the learning efficiency with batch normalization and shortcut connections. To demonstrate feasibility, we showed that medGAN generates synthetic patient records that achieve comparable performance to real data on many experiments including distribution statistics, predictive modeling tasks and a medical expert review. We also empirically observe a limited privacy risk in both identity and attribute disclosure using medGAN.

Erman Pattuk, Murat Kantarcioglu, Huseyin Ulusoy et al.

Secure multi-party computation (SMC) techniques are increasingly becoming more efficient and practical thanks to many recent novel improvements. The recent work have shown that different protocols that are implemented using different sharing mechanisms (e.g., boolean, arithmetic sharings, etc.) may have different computational and communication costs. Although there are some works that automatically mix protocols of different sharing schemes to fasten execution, none of them provide a generic optimization framework to find the cheapest mixed-protocol SMC execution for cloud deployment. In this work, we propose a generic SMC optimization framework CheapSMC that can use any mixed-protocol SMC circuit evaluation tool as a black-box to find the cheapest SMC cloud deployment option. To find the cheapest SMC protocol, CheapSMC runs one time benchmarks for the target cloud service and gathers performance statistics for basic circuit components. Using these performance statistics, optimization layer of CheapSMC runs multiple heuristics to find the cheapest mix-protocol circuit evaluation. Later on, the optimized circuit is passed to a mix-protocol SMC tool for actual executable generation. Our empirical results gathered by running different cases studies show that significant cost savings could be achieved using our optimization framework.

Muhammad Naveed, Erman Ayday, Ellen W. Clayton et al.

Genome sequencing technology has advanced at a rapid pace and it is now possible to generate highly-detailed genotypes inexpensively. The collection and analysis of such data has the potential to support various applications, including personalized medical services. While the benefits of the genomics revolution are trumpeted by the biomedical community, the increased availability of such data has major implications for personal privacy; notably because the genome has certain essential features, which include (but are not limited to) (i) an association with traits and certain diseases, (ii) identification capability (e.g., forensics), and (iii) revelation of family relationships. Moreover, direct-to-consumer DNA testing increases the likelihood that genome data will be made available in less regulated environments, such as the Internet and for-profit companies. The problem of genome data privacy thus resides at the crossroads of computer science, medicine, and public policy. While the computer scientists have addressed data privacy for various data types, there has been less attention dedicated to genomic data. Thus, the goal of this paper is to provide a systematization of knowledge for the computer science community. In doing so, we address some of the (sometimes erroneous) beliefs of this field and we report on a survey we conducted about genome data privacy with biomedical specialists. Then, after characterizing the genome privacy problem, we review the state-of-the-art regarding privacy attacks on genomic data and strategies for mitigating such attacks, as well as contextualizing these attacks from the perspective of medicine and public policy. This paper concludes with an enumeration of the challenges for genome data privacy and presents a framework to systematize the analysis of threats and the design of countermeasures as the field moves forward.