Managing ML-Based Application Non-Functional Behavior: A Multi-Model Approach

Modern applications are increasingly driven by Machine Learning (ML) models whose non-deterministic behavior is affecting the entire application life cycle from design to operation. The pervasive adoption of ML is urgently calling for approaches that guarantee a stable non-functional behavior of ML-based applications over time and across model changes. To this aim, non-functional properties of ML models, such as privacy, confidentiality, fairness, and explainability, must be monitored, verified, and maintained. This need is even more pressing when modern applications operate in the edge-cloud continuum, increasing their complexity and dynamicity. Existing approaches mostly focus on i) implementing classifier selection solutions according to the functional behavior of ML models, ii) finding new algorithmic solutions to this need, such as continuous re-training. In this paper, we propose a multi-model approach built on dynamic classifier selection, where multiple ML models showing similar non-functional properties are made available to the application and one model is selected over time according to (dynamic and unpredictable) contextual changes. Our solution goes beyond the state of the art by providing an architectural and methodological approach that continuously guarantees a stable non-functional behavior of ML-based applications, is applicable to different ML models, and is driven by non-functional properties assessed on the models themselves. It consists of a two-step process working during application operation, where model assessment verifies non-functional properties of ML models trained and selected at development time, and model substitution guarantees a continuous and stable support of non-functional properties. We experimentally evaluate our solution in a real-world scenario focusing on non-functional property fairness.

Towards Certification of Machine Learning-Based Distributed Systems

Machine Learning (ML) is increasingly used to drive the operation of complex distributed systems deployed on the cloud-edge continuum enabled by 5G. Correspondingly, distributed systems' behavior is becoming more non-deterministic in nature. This evolution of distributed systems requires the definition of new assurance approaches for the verification of non-functional properties. Certification, the most popular assurance technique for system and software verification, is not immediately applicable to systems whose behavior is determined by Machine Learning-based inference. However, there is an increasing push from policy makers, regulators, and industrial stakeholders towards the definition of techniques for the certification of non-functional properties (e.g., fairness, robustness, privacy) of ML. This article analyzes the challenges and deficiencies of current certification schemes, discusses open research issues and proposes a first certification scheme for ML-based distributed systems.

On the Robustness of Ensemble-Based Machine Learning Against Data Poisoning

Machine learning is becoming ubiquitous. From financial to medicine, machine learning models are boosting decision-making processes and even outperforming humans in some tasks. This huge progress in terms of prediction quality does not however find a counterpart in the security of such models and corresponding predictions, where perturbations of fractions of the training set (poisoning) can seriously undermine the model accuracy. Research on poisoning attacks and defenses even predates the introduction of deep neural networks, leading to several promising solutions. Among them, ensemble-based defenses, where different models are trained on portions of the training set and their predictions are then aggregated, are getting significant attention, due to their relative simplicity and theoretical and practical guarantees. The work in this paper designs and implements a hash-based ensemble approach for ML robustness and evaluates its applicability and performance on random forests, a machine learning model proved to be more resistant to poisoning attempts on tabular datasets. An extensive experimental evaluation is carried out to evaluate the robustness of our approach against a variety of attacks, and compare it with a traditional monolithic model based on random forests.