Related papers: Engineering Safety in Machine Learning

Effective software safety standards will contribute to confidence, or assurance, in the safety of the systems in which the software is used. It is infeasible to demonstrate a correlation between standards and accidents, but there is an…

This paper reviews the entire engineering process of trustworthy Machine Learning (ML) algorithms designed to equip critical systems with advanced analytics and decision functions. We start from the fundamental principles of ML and describe…

Artificial intelligence risks are multidimensional in nature, as the same risk scenarios may have legal, operational, and financial risk dimensions. With the emergence of new AI regulations, the state of the art of artificial intelligence…

Secure robotics is a multi-disciplinary endeavour for improving the cybersecurity posture of robotic and embodied Artificial Intelligence systems. The article surveys emerging concepts and ideas encapsulating the notion of secure robotics…

We introduce a novel simulation-based approach to identify hazards that result from unexpected worker behavior in human-robot collaboration. Simulation-based safety testing must take into account the fact that human behavior is variable and…

Human-in-the-loop aims to train an accurate prediction model with minimum cost by integrating human knowledge and experience. Humans can provide training data for machine learning applications and directly accomplish tasks that are hard for…

Predictions and forecasts of machine learning models should take the form of probability distributions, aiming to increase the quantity of information communicated to end users. Although applications of probabilistic prediction and…

A central question in machine learning is how reliable the predictions of a trained model are. Reliability includes the identification of instances for which a model is likely not to be trusted based on an analysis of the learning system…

Machine learning (ML) plays an ever-increasing role in advanced automotive functionality for driver assistance and autonomous operation; however, its adequacy from the perspective of safety certification remains controversial. In this…

We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through scheming. Scheming is a potential threat model where AI…

Machine learning develops rapidly, which has made many theoretical breakthroughs and is widely applied in various fields. Optimization, as an important part of machine learning, has attracted much attention of researchers. With the…

Continued adoption of agricultural robots postulates the farmer's trust in the reliability, robustness and safety of the new technology. This motivates our work on safety assurance of agricultural robots, particularly their ability to…

Governments, industry, and academia have undertaken efforts to identify and mitigate harms in ML-driven systems, with a particular focus on social and ethical risks of ML components in complex sociotechnical systems. However, existing…

Many applied settings in empirical economics involve simultaneous estimation of a large number of parameters. In particular, applied economists are often interested in estimating the effects of many-valued treatments (like teacher effects…

Predictive models are one of the most important techniques that are widely applied in many areas of software engineering. There have been a large number of primary studies that apply predictive models and that present well-preformed studies…

Trusting machine learning algorithms requires having confidence in their outputs. Confidence is typically interpreted in terms of model reliability, where a model is reliable if it produces a high proportion of correct outputs. However,…

The development and deployment of machine learning (ML) systems can be executed easily with modern tools, but the process is typically rushed and means-to-an-end. The lack of diligence can lead to technical debt, scope creep and misaligned…

While artificial-intelligence-based methods suffer from lack of transparency, rule-based methods dominate in safety-critical systems. Yet, the latter cannot compete with the first ones in robustness to multiple requirements, for instance,…

Following the recent surge in adoption of machine learning (ML), the negative impact that improper use of ML can have on users and society is now also widely recognised. To address this issue, policy makers and other stakeholders, such as…

By exploiting the increasing surface attack of systems, cyber-attacks can cause catastrophic events, such as, remotely disable safety mechanisms. This means that in order to avoid hazards, safety and security need to be integrated,…