The paper’s main contributions are twofold: to demonstrate how to apply the general European Union’s High-Level Expert Group’s (EU HLEG) guidelines for trustworthy AI in practice for the domain of healthcare; and to investigate the research question of what does “trustworthy AI” mean at the time of the COVID-19 pandemic. To this end, we present the results of a post-hoc self-assessment to evaluate the trustworthiness of an AI system for predicting a multi-regional score conveying the degree of lung compromise in COVID-19 patients, developed and verified by an interdisciplinary team with members from academia, public hospitals, and industry in time of pandemic. The AI system aims to help radiologists to estimate and communicate the severity of damage in a patient’s lung from Chest X-rays. It has been experimentally deployed in the radiology department of the ASST Spedali Civili clinic in Brescia (Italy) since December 2020 during pandemic time. The methodology we have applied for our post-hoc assessment, called Z-Inspection, uses socio-technical scenarios to identify ethical, technical and domain-specific issues in the use of the AI system in the context of the pandemic.
17 June 2008 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Formal verification is an important issue in circuit and system design. In this context, bounded model checking (BMC) is one of the most successful techniques. However, even if all the specified properties can be verified, it is difficult to determine whether they cover the complete functional behavior of a design. We propose a practical approach to analyze coverage in BMC. The approach can easily be integrated in a BMC tool with only minor changes. In our approach, a coverage property is generated for each important signal. If the considered properties do not describe the signal's entire behavior, the coverage property fails, and a counter example is generated. From the counter example, an uncovered scenario can be derived. This way, the approach also helps in design understanding. We demonstrate our method for a reduced instruction set computer (RISC) CPU. First, the coverage of the block-level verification is considered. Second, it is demonstrated how the technique can be applied on a higher level. Therefore, we investigate the instruction set verification of the RISC CPU. The experiments show that the costs for coverage analysis are comparable to the verification costs. Based on the results, we identified coverage gaps during the verification. We were able to close all of them and achieved 100% functional coverage in total.
During their life-cycle, modern connected cars will have to face various and changing security threats. As for any critical embedded system, security fixes in the form of software updates need to be thoroughly verified and cannot be deployed on a daily basis. The system needs to commit to a defense strategy, while attackers can examine vulnerabilities and prepare possible exploits before attacking. In order to break this asymmetry, it can be advantageous to use proactive defenses, such as reconfiguring parts of the system configuration. However, resource constraints and losses in quality of service need to be taken into account for such Moving Target Defenses (MTDs). In this article, we present a game-theoretic model that can be used to compute an optimal MTD defense for a critical embedded system that is facing several attackers with different objectives. The game is resolved using off-the-shelf MILP solvers. We validated the method with an automotive use case and conducted extensive experiments to evaluate its scalability and stability.