A Systematic Approach for Evaluating Artificial Intelligence Models in Industrial Settings.

Artificial Intelligence (AI) is one of the hottest topics in our society, especially when it comes to solving data-analysis problems. Industry are conducting their digital shifts, and AI is becoming a cornerstone technology for making decisions out of the huge amount of (sensors-based) data available in the production floor. However, such technology may be disappointing when deployed in real conditions. Despite good theoretical performances and high accuracy when trained and tested in isolation, a Machine-Learning (M-L) model may provide degraded performances in real conditions. One reason may be fragility in treating properly unexpected or perturbed data. The objective of the paper is therefore to study the robustness of seven M-L and Deep-Learning (D-L) algorithms, when classifying univariate time-series under perturbations. A systematic approach is proposed for artificially injecting perturbations in the data and for evaluating the robustness of the models. This approach focuses on two perturbations that are likely to happen during data collection. Our experimental study, conducted on twenty sensors' datasets from the public University of California Riverside (UCR) repository, shows a great disparity of the models' robustness under data quality degradation. Those results are used to analyse whether the impact of such robustness can be predictable-thanks to decision trees-which would prevent us from testing all perturbations scenarios. Our study shows that building such a predictor is not straightforward and suggests that such a systematic approach needs to be used for evaluating AI models' robustness.

Expanding COVID-19 symptom screening to retail, restaurants, and schools by preserving privacy using relaxed digital signatures

Symptom screening is a widely deployed strategy to mitigate the COVID-19 pandemic and many public health authorities are mandating its use by employers for all employees in the workplace. While symptom screening has the benefit of reducing the number of infected individuals in the workplace, it raises some inherently difficult privacy issues as a traditional approach requires the employer to collect symptom data from each employee which is essentially medical information. In this paper, we describe a system to implement Cryptographic Anonymous Symptom Screening (CASS) which allows for individuals to perform COVID symptom screening anonymously while avoiding the privacy issues of traditional approaches. In the system, individuals report their symptoms without any identifying information and are issued a completion certificate. This certificate contains a cryptographic code which certifies that the certificate was obtained from the screener after reporting no symptoms. The codes can be verified using a cryptographic algorithm which is publicly available. A standard cryptography approach to implement such a system would be to use digital signatures. Unfortunately, standard digital signatures have some limitations for this application in that the signatures are often hundreds of characters long and if the signature contains the name of the individual, then there is also a risk of compromising privacy. In our approach, we develop and utilize a relaxed digital signature scheme to provide 16 character long codes and handle names using equivalence classes which helps preserve privacy. Both of these extensions technically compromise the security but in a way that is negligible for this application. Our system can either serve the function of standard symptom screening system approaches for employees, but can also extend symptom screening to non-employees such as visitors or customers. In this case, the system can be utilized in retail, restaurants and schools to ensure that everyone in the physical space, including employees, customers, visitors and students have performed symptom screening.