相关论文: Framework for Certification of AI-Based Systems

Deep neural networks have become widely used, obtaining remarkable results in domains such as computer vision, speech recognition, natural language processing, audio recognition, social network filtering, machine translation, and…

Aerodynamic analysis during aircraft design usually involves methods of varying accuracy and spatial resolution, which all have their advantages and disadvantages. It is therefore desirable to create data-driven models which effectively…

In recent years, machine learning (ML) and neural networks (NNs) have gained widespread use and attention across various domains, particularly in transportation for achieving autonomy, including the emergence of flying taxis for urban air…

Verification of complex, safety-critical systems is a significant challenge. Manual testing and simulations are often used, but are only capable of exploring a subset of the system's reachable states. Formal methods are mathematically-based…

Deep neural networks (DNN) are growing in capability and applicability. Their effectiveness has led to their use in safety critical and autonomous systems, yet there is a dearth of cost-effective methods available for reasoning about the…

Providing formal guarantees of algorithmic fairness is of paramount importance to socially responsible deployment of machine learning algorithms. In this work, we study formal guarantees, i.e., certificates, for individual fairness (IF) of…

Neural networks are increasingly applied to support decision making in safety-critical applications (like autonomous cars, unmanned aerial vehicles and face recognition based authentication). While many impressive static verification…

Randomized smoothing-based certification is an effective approach for obtaining robustness certificates of deep neural networks (DNNs) against adversarial attacks. This method constructs a smoothed DNN model and certifies its robustness…

This paper focuses on the identification of dynamical systems with tailor-made model structures, where neural networks are used to approximate uncertain components and domain knowledge is retained, if available. These model structures are…

Aerial image registration or matching is a geometric process of aligning two aerial images captured in different environments. Estimating the precise transformation parameters is hindered by various environments such as time, weather, and…

AI Assurance -- producing the machine-readable evidence required to demonstrate compliance with AI governance frameworks -- has mature policy scaffolding but lacks the infrastructure to operationalize it. Organizations building high-risk AI…

Focus of this work is to recognize standards and further features directly from 3D CAD models. For this reason, a neural network was trained to recognize nine classes of machine elements. After the system identified a part as a standard,…

Neural networks predictions are unreliable when the input sample is out of the training distribution or corrupted by noise. Being able to detect such failures automatically is fundamental to integrate deep learning algorithms into robotics.…

Numerical software are widely used in safety-critical systems such as aircrafts, satellites, car engines and so on, facilitating dynamics control of such systems in real time, it is therefore absolutely necessary to verify their…

In this paper we present theory and algorithms enabling classes of Artificial Intelligence (AI) systems to continuously and incrementally improve with a-priori quantifiable guarantees - or more specifically remove classification errors -…

In the past decade, Artificial Intelligence (AI) has become a part of our daily lives due to major advances in Machine Learning (ML) techniques. In spite of an explosive growth in the raw AI technology and in consumer facing applications on…

Formal verification provides critical security assurances for neural networks, yet its practical application suffers from the long verification time. This work introduces a novel method for training verification-friendly neural networks,…

The growing AI field faces trust, transparency, fairness, and discrimination challenges. Despite the need for new regulations, there is a mismatch between regulatory science and AI, preventing a consistent framework. A five-layer nested…

Autonomous systems are often deployed in complex sociotechnical environments, such as public roads, where they must behave safely and securely. Unlike many traditionally engineered systems, autonomous systems are expected to behave…

Formal verification of neural networks is essential for their deployment in safety-critical areas. Many available formal verification methods have been shown to be instances of a unified Branch and Bound (BaB) formulation. We propose a…