An official website of the United States government
Abstract—Protection of cache hierarchies from side-channel attacks is critical for building secure systems, particularly the ones using Trusted Execution Environments (TEEs). In this pa- per, we consider the problem of efficient and secure fine-grained partitioning of cache hierarchies and propose a framework, called Secure Hierarchies for TEEs (TEE-SHirT). In the context of a three-level cache system, TEE-SHirT consists of partitioned shared last-level cache, partitioned private L2 caches, and non- partitioned L1 caches that are flushed on context switches and system calls. Efficient and correct partitioning requires careful design. Towards this goal, TEE-SHirT makes three contributions: 1) we demonstrate how the hardware structures used for holding cache partitioning metadata can be effectively virtualized to avoid flushing of cache partition content on context switches and system calls; 2) we show how to support multi-threaded enclaves in TEE- SHirT, addressing the issues of coherency and consistency that arise with both intra-core and inter-core data sharing; 3) we develop a formal security model for TEE-SHirT to rigorously reason about the security of our design.
more »
« less
Counterfactual and Factual Reasoning over Hypergraphs for Interpretable Clinical Predictions on EHR
Electronic Health Record modeling is crucial for digital medicine. However, existing models ignore higher-order interactions among medical codes and their causal relations towards downstream clinical predictions. To address such limitations, we propose a novel framework CACHE, to provide effective and insightful clinical predictions based on hypergraph representation learning and counterfactual and factual reasoning techniques. Experiments on two real EHR datasets show the superior performance of CACHE. Case studies with a domain expert illustrate a preferred capability of CACHE in generating clinically meaningful interpretations towards the correct predictions.
more »
« less
- PAR ID:
- 10391649
- Date Published:
- Journal Name:
- Proceedings of the 2nd Machine Learning for Health symposium
- Volume:
- 193
- Page Range / eLocation ID:
- 259-278
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Summary In many clinical settings, a patient outcome takes the form of a scalar time series with a recovery curve shape, which is characterized by a sharp drop due to a disruptive event (e.g., surgery) and subsequent monotonic smooth rise towards an asymptotic level not exceeding the pre-event value. We propose a Bayesian model that predicts recovery curves based on information available before the disruptive event. A recovery curve of interest is the quantified sexual function of prostate cancer patients after prostatectomy surgery. We illustrate the utility of our model as a pre-treatment medical decision aid, producing personalized predictions that are both interpretable and accurate. We uncover covariate relationships that agree with and supplement that in existing medical literature.more » « less
-
Abstract Sudden cardiac death from arrhythmia is a major cause of mortality worldwide. In this study, we developed a novel deep learning (DL) approach that blends neural networks and survival analysis to predict patient-specific survival curves from contrast-enhanced cardiac magnetic resonance images and clinical covariates for patients with ischemic heart disease. The DL-predicted survival curves offer accurate predictions at times up to 10 years and allow for estimation of uncertainty in predictions. The performance of this learning architecture was evaluated on multi-center internal validation data and tested on an independent test set, achieving concordance indexes of 0.83 and 0.74 and 10-year integrated Brier scores of 0.12 and 0.14. We demonstrate that our DL approach, with only raw cardiac images as input, outperforms standard survival models constructed using clinical covariates. This technology has the potential to transform clinical decision-making by offering accurate and generalizable predictions of patient-specific survival probabilities of arrhythmic death over time.more » « less
-
Abstract We present our continuous efforts from a modeling and numerical viewpoint to develop a powerful and flexible mathematical and computational framework called Ocular Mathematical Virtual Simulator (OMVS). The OMVS aims to solve problems arising in biomechanics and hemodynamics within the human eye. We discuss our contribution towards improving the reliability and reproducibility of computational studies by performing a thorough validation of the numerical predictions against experimental data. The OMVS proved capable of simulating complex multiphysics and multiscale scenarios motivated by the study of glaucoma. Furthermore, its modular design allows the continuous integration of new models and methods as the research moves forward, and supports the utilization of the OMVS as a promising non‐invasive clinical investigation tool for personalized research in ophthalmology.more » « less
-
Abstract We introduce a statistical procedure that integrates datasets from multiple biomedical studies to predict patients' survival, based on individual clinical and genomic profiles. The proposed procedure accounts for potential differences in the relation between predictors and outcomes across studies, due to distinct patient populations, treatments and technologies to measure outcomes and biomarkers. These differences are modeled explicitly with study‐specific parameters. We use hierarchical regularization to shrink the study‐specific parameters towards each other and to borrow information across studies. The estimation of the study‐specific parameters utilizes a similarity matrix, which summarizes differences and similarities of the relations between covariates and outcomes across studies. We illustrate the method in a simulation study and using a collection of gene expression datasets in ovarian cancer. We show that the proposed model increases the accuracy of survival predictions compared to alternative meta‐analytic methods.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
