Related papers: Towards Quantification of Assurance for Learning-e…

With the increasing capabilities of machine learning systems and their potential use in safety-critical systems, ensuring high-quality data is becoming increasingly important. In this paper we present a novel approach for the assurance of…

The introduction of the Segment Anything Model (SAM) has paved the way for numerous semantic segmentation applications. For several tasks, quantifying the uncertainty of SAM is of particular interest. However, the ambiguous nature of the…

Algorithmic assurances from advanced autonomous systems assist human users in understanding, trusting, and using such systems appropriately. Designing these systems with the capacity of assessing their own capabilities is one approach to…

The increasing use of machine-learning (ML) enabled systems in critical tasks fuels the quest for novel verification and validation techniques yet grounded in accepted system assurance principles. In traditional system development,…

Hardware vulnerabilities are generally considered more difficult to fix than software ones because they are persistent after fabrication. Thus, it is crucial to assess the security and fix the vulnerabilities at earlier design phases, such…

Uncertainty quantification is a key pillar of trustworthy machine learning. It enables safe reactions under unsafe inputs, like predicting only when the machine learning model detects sufficient evidence, discarding anomalous data, or…

Autonomous and semi-autonomous systems are using deep learning models to improve decision-making. However, deep classifiers can be overly confident in their incorrect predictions, a major issue especially in safety-critical domains. The…

To provide safety guarantees for learning-based control systems, recent work has developed formal verification methods to apply after training ends. However, if the trained policy does not meet the specifications, or there is conservatism…

Uncertainty quantification is essential when deploying learning-based control methods in safety-critical systems. This is commonly realized by constructing uncertainty tubes that enclose the unknown function of interest, e.g., the reward…

We apply a compositional formal modeling and verification method to an autonomous aircraft taxi system. We provide insights into the modeling approach and we identify several research areas where further development is needed. Specifically,…

In this thesis a comprehensive verification framework is proposed to contend with some important issues in composability verification and a verification process is suggested to verify composability of different kinds of systems models, such…

EASA's learning-assurance guidance requires data-driven aviation systems to build and monitor their own situation representation, yet for neural networks the technical means to provide such evidence remain an open problem. We address this…

Quantization is a promising technique for reducing the bit-width of deep models to improve their runtime performance and storage efficiency, and thus becomes a fundamental step for deployment. In real-world scenarios, quantized models are…

Uncertainty quantification is crucial to assess prediction quality of a machine learning model. In the case of Extreme Learning Machines (ELM), most methods proposed in the literature make strong assumptions on the data, ignore the…

Automated Essay Scoring (AES) systems now reach near human agreement on some public benchmarks, yet real-world adoption, especially in high-stakes examinations, remains limited. A principal obstacle is that most models output a single score…

On top of machine learning models, uncertainty quantification (UQ) functions as an essential layer of safety assurance that could lead to more principled decision making by enabling sound risk assessment and management. The safety and…

Autonomous vehicles rely on machine learning to solve challenging tasks in perception and motion planning. However, automotive software safety standards have not fully evolved to address the challenges of machine learning safety such as…

Many systems contain latent variables that make their dynamics partially unidentifiable or cause distribution shifts in the observed statistics between offline and online data. However, existing control techniques often assume access to…

Machine learning components such as deep neural networks are used extensively in Cyber-Physical Systems (CPS). However, such components may introduce new types of hazards that can have disastrous consequences and need to be addressed for…

In learning-enabled autonomous systems, safety monitoring of learned components is crucial to ensure their outputs do not lead to system safety violations, given the operational context of the system. However, developing a safety monitor…