Related papers: Mitigating Downstream Model Risks via Model Proven…
Trained machine learning models are increasingly used to perform high-impact tasks in areas such as law enforcement, medicine, education, and employment. In order to clarify the intended use cases of machine learning models and minimize…
The rapid adoption of open source machine learning (ML) datasets and models exposes today's AI applications to critical risks like data poisoning and supply chain attacks across the ML lifecycle. With growing regulatory pressure to address…
Recent years have witnessed a growing interest for time series foundation models, with a strong emphasis on the forecasting task. Yet, the crucial task of out-of-domain imputation of missing values remains largely underexplored. We propose…
Design of large software systems requires rigorous application of software engineering methods covering all phases of the software process. Debugging during the early design phases is extremely important, because late bug-fixes are…
Interest has been growing in decision-focused machine learning methods which train models to account for how their predictions are used in downstream optimization problems. Doing so can often improve performance on subsequent decision…
Fairness of machine learning models in healthcare has drawn increasing attention from clinicians, researchers, and even at the highest level of government. On the other hand, the importance of developing and deploying interpretable or…
Machine Unlearning (MUL) is crucial for privacy protection and content regulation, yet recent studies reveal that traces of forgotten information persist in unlearned models, enabling adversaries to resurface removed knowledge. Existing…
Designing sustainable systems involves complex interactions between environmental resources, social impact/adoption, and financial costs/benefits. In a constrained world, achieving a balanced design across those dimensions has become…
As machine learning (ML) components become increasingly integrated into software systems, the emphasis on the ethical or responsible aspects of their use has grown significantly. This includes building ML-based systems that adhere to…
In this paper, we propose a method for aligning models with their realization through the application of model-based systems engineering. Our approach is divided into three steps. (1) Firstly, we leverage domain expertise and the Unified…
To improve real-world applications of machine learning, experienced modelers develop intuition about their datasets, their models, and how the two interact. Manual inspection of raw data - of representative samples, of outliers, of…
The quality and correct functioning of software components embedded in electronic systems are of utmost concern especially for safety and mission-critical systems. Model-based testing and formal verification techniques can be employed to…
Model merging has achieved significant success, with numerous innovative methods proposed to enhance capabilities by combining multiple models. However, challenges persist due to the lack of a unified framework for classification and…
As machine- and AI-generated content proliferates, protecting the intellectual property of generative models has become imperative, yet verifying data ownership poses formidable challenges, particularly in cases of unauthorized reuse of…
Managing models in a consistent manner is an important task in the field of Model-Driven Engineering (MDE). Although restoring and maintaining consistency is desired in general, recent work has pointed out that always strictly enforcing…
This article introduces a metamodel for the Business Model Canvas (BMC) using the Unified Modelling Language (UML), together with a dedicated Domain-Specific Modelling Language (DSML) tool. Although the BMC is widely adopted by both…
The adoption of machine learning in applications where it is crucial to ensure fairness and accountability has led to a large number of model proposals in the literature, largely formulated as optimisation problems with constraints reducing…
Artificial Intelligence has gained a lot of traction in the recent years, with machine learning notably starting to see more applications across a varied range of fields. One specific machine learning application that is of interest to us…
Large-scale Machine Learning (ML) based Software Systems are increasingly developed by distributed teams situated in different trust domains. Insider threats can launch attacks from any domain to compromise ML assets (models and datasets).…
Federated Learning (FL) presents a promising paradigm for training machine learning models across decentralized edge devices while preserving data privacy. Ensuring the integrity and traceability of data across these distributed…