Modeling Ethical and Operational Preferences in Automated Driving Systems

Whereas automated driving technology has made tremendous gains in the last decade, significant questions remain regarding its integration into society. Given its revolutionary nature, the use of automated driving systems (ADSs) is accompanied by myriad novel quandaries relating to both operational and ethical concerns that are relevant to numerous stakeholders (e.g., governments, manufacturers, and passengers). When considering any such problem, the ADS’s decision-making calculus is always a central component. This is true for concerns about public perception and trust to others regarding explainability and legal certainty. Therefore, in this manuscript, we set forth a general decision-analytic framework tailorable to multitudinous stakeholders. More specifically, we develop and validate a generic tree of ADS management objectives, explore potential attributes for their measurement, and provide multiattribute utility functions for implementation. Given the contention surrounding numerous ethical concerns in ADS operations, we explore how each of the aforementioned components can be tailored in accordance with the stakeholder’s desired ethical perspective. A simulation environment is developed upon which our framework is tested. Within this environment we illustrate how our approach can be leveraged by stakeholders to make strategic trade-offs regarding ADS behavior and to inform policymaking efforts. In so doing, our framework is demonstrated as a practical, tractable, and transparent means of modeling ADS decision making.

AI in drug development: a multidisciplinary perspective

The introduction of a new drug to the commercial market follows a complex and long process that typically spans over several years and entails large monetary costs due to a high attrition rate. Because of this, there is an urgent need to improve this process using innovative technologies such as artificial intelligence (AI). Different AI tools are being applied to support all four steps of the drug development process (basic research for drug discovery; pre-clinical phase; clinical phase; and postmarketing). Some of the main tasks where AI has proven useful include identifying molecular targets, searching for hit and lead compounds, synthesising drug-like compounds and predicting ADME-Tox. This review, on the one hand, brings in a mathematical vision of some of the key AI methods used in drug development closer to medicinal chemists and, on the other hand, brings the drug development process and the use of different models closer to mathematicians. Emphasis is placed on two aspects not mentioned in similar surveys, namely, Bayesian approaches and their applications to molecular modelling and the eventual final use of the methods to actually support decisions. Promoting a perfect synergy.

An Adversarial Risk Analysis Framework for Batch Acceptance Problems

We provide an adversarial risk analysis framework for batch acceptance problems in which a decision maker relies exclusively on the size of the batch to accept or reject its admission to a system, albeit being aware of the presence of an opponent. The adversary acts as a data-fiddler attacker perturbing the observations perceived by the decision maker through injecting faulty items and/or modifying the existing items to faulty ones. We develop optimal policies against this combined attack strategy and illustrate the methodology with a review spam example.

Variationally Inferred Sampling through a Refined Bound

In this work, a framework to boost the efficiency of Bayesian inference in probabilistic models is introduced by embedding a Markov chain sampler within a variational posterior approximation. We call this framework "refined variational approximation". Its strengths are its ease of implementation and the automatic tuning of sampler parameters, leading to a faster mixing time through automatic differentiation. Several strategies to approximate evidence lower bound (ELBO) computation are also introduced. Its efficient performance is showcased experimentally using state-space models for time-series data, a variational encoder for density estimation and a conditional variational autoencoder as a deep Bayes classifier.

Protecting From Malware Obfuscation Attacks Through Adversarial Risk Analysis

Malware constitutes a major global risk affecting millions of users each year. Standard algorithms in detection systems perform insufficiently when dealing with malware passed through obfuscation tools. We illustrate this studying in detail an open source metamorphic software, making use of a hybrid framework to obtain the relevant features from binaries. We then provide an improved alternative solution based on adversarial risk analysis which we illustrate describe with an example.

Risk Analysis for Unintentional Slide Deployment During Airline Operations

We present a risk analysis undertaken to mitigate problems in relation to the unintended deployment of slides under normal operations within a commercial airline. This type of incident entails relevant costs for the airline industry. After assessing the likelihood and severity of its consequences, we conclude that such risks need to be managed. We then evaluate the effectiveness of various countermeasures, describing and justifying the chosen ones. We also discuss several issues faced when implementing and communicating the proposed measures, thus fully illustrating the risk analysis process.

Issues in Bayesian Analysis of Neural Network Models

Stemming from work by Buntine and Weigend (1991) and MacKay (1992), there is a growing interest in Bayesian analysis of neural network models. Although conceptually simple, this problem is computationally involved. We suggest a very efficient Markov chain Monte Carlo scheme for inference and prediction with fixed&hyphenarchitecture feedforward neural networks. The scheme is then extended to the variable architecture case, providing a data&hyphendriven procedure to identify sensible architectures.