Ensuring safety and explainability of machine learning (ML) is a topic of increasing relevance as data-driven applications venture into safety-critical application domains, traditionally committed to high safety standards that are not satisfied with an exclusive testing approach of otherwise inaccessible black-box systems. Especially the interaction between safety and security is a central challenge, as security violations can lead to compromised safety. The contribution of this paper to addressing both safety and security within a single concept of protection applicable during the operation of ML systems is active monitoring of the behavior and the operational context of the data-driven system based on distance measures of the Empirical Cumulative Distribution Function (ECDF). We investigate abstract datasets (XOR, Spiral, Circle) and current security-specific datasets for intrusion detection (CICIDS2017) of simulated network traffic, using statistical distance measures including the Kolmogorov-Smirnov, Kuiper, Anderson-Darling, Wasserstein and mixed Wasserstein-Anderson-Darling measures. Our preliminary findings indicate that there is a meaningful correlation between ML decisions and the ECDF-based distances measures of the input features. Thus, they can provide a confidence level that can be used for a) analyzing the applicability of the ML system in a given field (safety/security) and b) analyzing if the field data was maliciously manipulated 1 .
As Cyber-Physical Systems (CPS) grow increasingly complex and interact with external CPS, system security remains a nontrivial challenge that continues to scale accordingly, with potentially devastating consequences if left unchecked. While there is a significant body of work on system security found in industry practice, manual diagnosis of security vulnerabilities is still widely applied. Such approaches are typically resource-intensive, scale poorly and introduce additional risk due to human error. In this paper, a model-based approach for Security Attack Tree analysis using the HiP-HOPS dependability analysis tool is presented. The approach is demonstrated within the context of a simple web-based medical application to automatically generate attack trees, encapsulated as Digital Dependability Identities (DDIs), for offline security analysis. The paper goes on to present how the produced DDIs can be used to approach security maintenance, identifying security capabilities and controls to counter diagnosed vulnerabilities.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.