Related papers: Certified Control for Train Sign Classification
Regular inspection of rail valves and engines is an important task to ensure the safety and efficiency of railway networks around the globe. Over the past decade, computer vision and pattern recognition based techniques have gained traction…
Noisy data, non-convex objectives, model misspecification, and numerical instability can all cause undesired behaviors in machine learning systems. As a result, detecting actual implementation errors can be extremely difficult. We…
Machine learning components such as deep neural networks are used extensively in Cyber-Physical Systems (CPS). However, they may introduce new types of hazards that can have disastrous consequences and need to be addressed for engineering…
Modern Code Review (MCR) is a standard in all kinds of organizations that develop software. MCR pays for itself through perceived and proven benefits in quality assurance and knowledge transfer. However, the time invest in MCR is generally…
Quality control is a key activity performed by manufacturing companies to verify product conformance to the requirements and specifications. Standardized quality control ensures that all the products are evaluated under the same criteria.…
Machine learning applications have become ubiquitous. Their applications range from embedded control in production machines over process optimization in diverse areas (e.g., traffic, finance, sciences) to direct user interactions like…
Programmable Logic Controllers (PLC) are widely used for industrial automation including safety systems at CERN. The incorrect behaviour of the PLC control system logic can cause significant financial losses by damage of property or the…
Automatic software verification tools help to find hard-to-detect faults in programs checked against specified requirements non-interactively. Besides, they can prove program correctness formally under certain assumptions. These…
The electrification of powertrains is rising as the objective for a more viable future is intensified. To ensure continuous and reliable operation without undesirable malfunctions, it is essential to monitor the internal temperatures of…
Monitoring of a signal plays an essential role in the runtime verification of cyber-physical systems. Qualitative timed pattern matching is one of the mathematical formulations of monitoring, which gives a Boolean verdict for each…
This position paper argues that formal optimal control theory should be central to AI alignment research, offering a distinct perspective from prevailing AI safety and security approaches. While recent work in AI safety and mechanistic…
Interlocking logics are at the core of critical systems controlling the traffic within stations. In this paper, we consider a generic interlocking logic, which can be instantiated to control a wide class of stations. We tackle the problem…
Formal verification has emerged as a powerful approach to ensure the safety and reliability of deep neural networks. However, current verification tools are limited to only a handful of properties that can be expressed as first-order…
In the ALICE experiment hundreds of users are analyzing big datasets on a Grid system. High throughput and short turn-around times are achieved by a centralized system called the LEGO trains. This system combines analysis from different…
While Chain-of-Thought (CoT) monitoring offers a unique opportunity for AI safety, this opportunity could be lost through shifts in training practices or model architecture. To help preserve monitorability, we propose a pragmatic way to…
Various mobility applications like advanced driver assistance systems increasingly utilize artificial intelligence (AI) based functionalities. Typically, deep neural networks (DNNs) are used as these provide the best performance on the…
As AI and machine-learned software are used increasingly for making decisions that affect humans, it is imperative that they remain fair and unbiased in their decisions. To complement design-time bias mitigation measures, runtime…
How effective are recent advancements in autonomous vehicle perception systems when applied to real-world autonomous vehicle control? While numerous vision-based autonomous vehicle systems have been trained and evaluated in simulated…
A significant part of contemporary research in autonomous vehicles is dedicated to the development of safety critical systems where state-of-the-art artificial intelligence (AI) algorithms, like computer vision (CV), can play a major role.…
Machine Learning (ML) is increasingly used to implement advanced applications with non-deterministic behavior, which operate on the cloud-edge continuum. The pervasive adoption of ML is urgently calling for assurance solutions assessing…