In July 2022, the Center for Security and Emerging Technology (CSET) at Georgetown University and the Program on Geopolitics, Technology, and Governance at the Stanford Cyber Policy Center convened a workshop of experts to examine the relationship between vulnerabilities in artificial intelligence systems and more traditional types of software vulnerabilities. Topics discussed included the extent to which AI vulnerabilities can be handled under standard cybersecurity processes, the barriers currently preventing the accurate sharing of information about AI vulnerabilities, legal issues associated with adversarial attacks on AI systems, and potential areas where government support could improve AI vulnerability management and mitigation. This report is meant to accomplish two things. First, it provides a high-level discussion of AI vulnerabilities, including the ways in which they are disanalogous to other types of vulnerabilities, and the current state of affairs regarding information sharing and legal oversight of AI vulnerabilities. Second, it attempts to articulate broad recommendations as endorsed by the majority of participants at the workshop.

The National Cancer Institute (NCI) Genomic Data Commons (GDC) contains more than 2.9 petabytes of genomic and associated clinical data from more than 60 NCI-funded and other contributed cancer genomics research projects. The GDC consists of five applications over a common data model and a common application programming interface.

Schizophrenia, Schizoaffective, and Bipolar disorders share behavioral and phenomenological traits, intermediate phenotypes, and some associated genetic loci with pleiotropic effects. Volumetric abnormalities in brain structures are among the intermediate phenotypes consistently reported associated with these disorders. In order to examine the genetic underpinnings of these structural brain modifications, we performed genome-wide association analyses (GWAS) on 60 quantitative structural brain MRI phenotypes in a sample of 777 subjects (483 cases and 294 controls pooled together). Genotyping was performed with the Illumina PsychChip microarray, followed by imputation to the 1000 genomes multiethnic reference panel. Enlargement of the Temporal Horns of Lateral Ventricles (THLV) is associated with an intronic SNP of the gene NRXN1 (rs12467877, P = 6.76E–10), which accounts for 4.5% of the variance in size. Enlarged THLV is associated with psychosis in this sample, and with reduction of the hippocampus and enlargement of the choroid plexus and caudate. Eight other suggestively significant associations ( P < 5.5E–8) were identified with THLV and 5 other brain structures. Although rare deletions of NRXN1 have been previously associated with psychosis, this is the first report of a common SNP variant of NRXN1 associated with enlargement of the THLV in psychosis.

Schizophrenia, Schizoaffective, and Bipolar Disorders share common illness traits, intermediate phenotypes and a partially overlapping polygenic basis. We performed GWAS on deep phenotyping data, including structural MRI and DTI, clinical, and behavioral scales from 1,115 cases and controls. Significant associations were observed with two cerebrospinal fluid volumes: the temporal horn of left lateral ventricle was associated with NRXN1 , and the volume of the cavum septum pellucidum was associated with LRP1B and RORA . Both volumes were associated with illness. Suggestive associations were observed with local gyrification indices, fractional anisotropy and age at onset. The deep phenotyping approach allowed unexpected genetic sharing to be found between phenotypes, including temporal horn of left lateral ventricle and age at onset.

The International Cancer Genome Consortium (ICGC)’s Pan-Cancer Analysis of Whole Genomes (PCAWG) project aimed to categorize somatic and germline variations in both coding and non-coding regions in over 2,800 cancer patients. To provide this dataset to the research working groups for downstream analysis, the PCAWG Technical Working Group marshalled ~800TB of sequencing data from distributed geographical locations; developed portable software for uniform alignment, variant calling, artifact filtering and variant merging; performed the analysis in a geographically and technologically disparate collection of compute environments; and disseminated high-quality validated consensus variants to the working groups. The PCAWG dataset has been mirrored to multiple repositories and can be located using the ICGC Data Portal. The PCAWG workflows are also available as Docker images through Dockstore enabling researchers to replicate our analysis on their own data.

Project Matsu is a collaboration between the Open Commons Consortium and NASA focused on developing open source technology for the cloud-based processing of Earth satellite imagery and for detecting fires and floods to help support natural disaster detection and relief. We describe a framework for efficient analysis and reanalysis of large amounts of data called the Matsu “Wheel” and the analytics used to process hyperspectral data produced daily by NASA’s Earth Observing-1 (EO-1) satellite. The wheel is designed to be able to support scanning queries using cloud computing applications, such as Hadoop and Accumulo. A scanning query processes all, or most, of the data in a database or data repository. In contrast, standard queries typically process a relatively small percentage of the data. The wheel is a framework in which multiple scanning queries are grouped together and processed in turn, over chunks of data from the database or repository. Over time, the framework brings all data to each group of scanning queries. With this approach, contention and the overall time to process all scanning queries can be reduced. We describe our Wheel analytics, including an anomaly detector for rare spectral signatures or anomalies in hyperspectral data and a land cover classifier that can be used for water and flood detection. The resultant products of the analytics are made accessible through an API for further distribution. The Matsu Wheel allows many shared data services to be performed together to efficiently use resources for processing hyperspectral satellite image data and other, e.g., large environmental datasets that may be analyzed for many purposes.

Project Matsu is a collaboration between the Open Commons Consortium and NASA focused on developing open source technology for the cloud-based processing of Earth satellite imagery. A particular focus is the development of applications for detecting fires and floods to help support natural disaster detection and relief. Project Matsu has developed an open source cloud-based infrastructure to process, analyze, and reanalyze large collections of hyperspectral satellite image data using OpenStack, Hadoop, MapReduce, Storm and related technologies. We describe a framework for efficient analysis of large amounts of data called the Matsu "Wheel." The Matsu Wheel is currently used to process incoming hyperspectral satellite data produced daily by NASA's Earth Observing-1 (EO-1) satellite. The framework is designed to be able to support scanning queries using cloud computing applications, such as Hadoop and Accumulo. A scanning query processes all, or most of the data, in a database or data repository. We also describe our preliminary Wheel analytics, including an anomaly detector for rare spectral signatures or thermal anomalies in hyperspectral data and a land cover classifier that can be used for water and flood detection. Each of these analytics can generate visual reports accessible via the web for the public and interested decision makers. The resultant products of the analytics are also made accessible through an Open Geospatial Compliant (OGC)-compliant Web Map Service (WMS) for further distribution. The Matsu Wheel allows many shared data services to be performed together to efficiently use resources for processing hyperspectral satellite image data and other, e.g., large environmental datasets that may be analyzed for many purposes.

BACKGROUND:As large genomics and phenotypic datasets are becoming more common, it is increasingly difficult for most researchers to access, manage, and analyze them. One possible approach is to provide the research community with several petabyte-scale cloud-based computing platforms containing these data, along with tools and resources to analyze it.METHODS:Bionimbus is an open source cloud-computing platform that is based primarily upon OpenStack, which manages on-demand virtual machines that provide the required computational resources, and GlusterFS, which is a high-performance clustered file system. Bionimbus also includes Tukey, which is a portal, and associated middleware that provides a single entry point and a single sign on for the various Bionimbus resources; and Yates, which automates the installation, configuration, and maintenance of the software infrastructure required.RESULTS:Bionimbus is used by a variety of projects to process genomics and phenotypic data. For example, it is used by an acute myeloid leukemia resequencing project at the University of Chicago. The project requires several computational pipelines, including pipelines for quality control, alignment, variant calling, and annotation. For each sample, the alignment step requires eight CPUs for about 12 h. BAM file sizes ranged from 5 GB to 10 GB for each sample.CONCLUSIONS:Most members of the research community have difficulty downloading large genomics datasets and obtaining sufficient storage and computer resources to manage and analyze the data. Cloud computing platforms, such as Bionimbus, with data commons that contain large genomics datasets, are one choice for broadening access to research data in genomics.