10,473 research outputs found
Modeling Threats to AI-ML Systems Using STRIDE
No full textThe application of emerging technologies, such as Artificial Intelligence (AI), entails risks that need to be addressed to ensure secure and trustworthy socio-technical infrastructures. Machine Learning (ML), the most developed subfield of AI, allows for improved decision-making processes. However, ML models exhibit specific vulnerabilities that conventional IT systems are not subject to. As systems incorporating ML components become increasingly pervasive, the need to provide security practitioners with threat modeling tailored to the specific AI-ML pipeline is of paramount importance. Currently, there exist no well-established approach accounting for the entire ML life-cycle in the identification and analysis of threats targeting ML techniques. In this paper, we propose an asset-centered methodology—STRIDE-AI—for assessing the security of AI-ML-based systems. We discuss how to apply the FMEA process to identify how assets generated and used at different stages of the ML life-cycle may fail. By adapting Microsoft’s STRIDE approach to the AI-ML domain, we map potential ML failure modes to threats and security properties these threats may endanger. The proposed methodology can assist ML practitioners in choosing the most effective security controls to protect ML assets. We illustrate STRIDE-AI with the help of a real-world use case selected from the TOREADOR H2020 project
The relevance of EEG monitoring for carotid endoarterectomy under local and general anestesia
No full textClinical outcome and olanzapine plasma levels in acute schizophrenia
No full textPURPOSE: This open label study was performed to evaluate the relationship between the plasma concentration of olanzapine and the response in acute schizophrenic inpatients.
MATERIAL AND METHODS: A total of 54 inpatients, 38 males and 16 females, age ranging from 18 to 75 years, affected by Schizophrenia (DSM IV criteria) during an exacerbation phase were included in the study. Olanzapine (OLZ) was started at a dose of 5-20 mg/day and was increased to a mean dose of 15.27 mg +/-5.53 S.D. Patients were evaluated at baseline, and after 2 weeks, by using BPRS, PANNS, HRS-D, EPSE, and ACS.
RESULTS: BPRS and total PANSS showed a statistically significant improvement at the end of the study. Olanzapine plasma levels (PL) ranged from 5 to 120 ng/ml (mean 33.15 ng/ml +/- 28.28 S.D.) and showed a positive correlation with OLZ dosage. A significant curvilinear correlation between OLZ PL and clinical improvement (BPRS, PANSS and HRS-D percent of amelioration) was observed.
CONCLUSION: Olanzapine plasma level determination seems to be a useful tool in optimizing acute treatment particularly for more problematic cases
Metadata Representations for Queryable ML Model Zoos
No full textMachine learning (ML) practitioners and organizations are building model zoos of pre-trained models, containing metadata describing properties of the ML models and datasets that are useful for reporting, auditing, reproducibility, and interpretability purposes. The metatada is currently not standardised; its expressivity is limited; and there is no interoperable way to store and query it. Consequently, model search, reuse, comparison, and composition are hindered. In this paper, we advocate for standardized ML model metadata representation and management, proposing a toolkit supported to help practitioners manage and query that metadata.Web Information SystemsHuman-Centred Artificial Intelligenc
A Manifesto of Nodalism
No full textThis paper proposes the notion of Nodalism as a means describing contemporary culture and of understanding my own creative practice in electronic music composition. It draws on theories and ideas from Kirby, Bauman, Bourriaud, Deleuze, Guatarri, and Gochenour, to demonstrate how networks of ideas or connectionist neural models of cognitive behaviour can be used to contextualize, understand and become a creative tool for the creation of contemporary electronic music
Optimizing ML Inference Queries Under Constraints
No full textThe proliferation of pre-trained ML models in public Web-based model zoos facilitates the engineering of ML pipelines to address complex inference queries over datasets and streams of unstructured content. Constructing optimal plan for a query is hard, especially when constraints (e.g. accuracy or execution time) must be taken into consideration, and the complexity of the inference query increases. To address this issue, we propose a method for optimizing ML inference queries that selects the most suitable ML models to use, as well as the order in which those models are executed. We formally define the constraint-based ML inference query optimization problem, formulate it as a Mixed Integer Programming (MIP) problem, and develop an optimizer that maximizes accuracy given constraints. This optimizer is capable of navigating a large search space to identify optimal query plans on various model zoos.Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.Web Information SystemsHuman-Centred Artificial Intelligenc
STRIDE-AI: An Approach to Identifying Vulnerabilities of Machine Learning Assets
No full textWe propose a security methodology for Machine Learning (ML) pipelines, supporting the definition of key security properties of ML assets, the identification of threats to them as well as the selection, test and verification of security controls. Our proposal is based on STRIDE, a widely used approach to threat modeling originally developed by Microsoft. We adapt STRIDE to the Artificial Intelligence domain by taking a security property-driven approach that also provides guidance in selecting the security controls needed to alleviate the identified threats. Our proposal is illustrated via an industrial case study
Synthesis Expansion: analisi di un sottogruppo di pazienti con eventi maggiori in territorio carotideo: interazioni tra trattamento fibrinolitico e grado di stenosi arteriosa extracranica
No full text
- …
