Related papers: Framework for Certification of AI-Based Systems

Context: Artificial intelligence (AI) has made its way into everyday activities, particularly through new techniques such as machine learning (ML). These techniques are implementable with little domain knowledge. This, combined with the…

During the development and verification of complex airborne systems, a variety of languages and development environments are used for different levels of the system hierarchy. As a result, there may be manual steps to translate requirements…

Utilising quantum computing technology to enhance artificial intelligence systems is expected to improve training and inference times, increase robustness against noise and adversarial attacks, and reduce the number of parameters without…

Training certifiably robust neural networks is an important but challenging task. While many algorithms for (deterministic) certified training have been proposed, they are often evaluated on different training schedules, certification…

Data-driven approaches are becoming more common as problem-solving techniques in many areas of research and industry. In most cases, machine learning models are the key component of these solutions, but a solution involves multiple such…

AI-supported programming has arrived, as shown by the introduction and successes of large language models for code, such as Copilot/Codex (Github/OpenAI) and AlphaCode (DeepMind). Above human average performance on programming challenges is…

As autonomy becomes prevalent in many applications, ranging from recommendation systems to fully autonomous vehicles, there is an increased need to provide safety guarantees for such systems. The problem is difficult, as these are large,…

The use of Artificial Intelligence (AI) in high-risk, decision-making scenarios presents technical, safety, and normative challenges; problems that may only be ameliorated by human oversight. However, notions of human oversight lack a…

As the potential for neural networks to augment our daily lives grows, ensuring their quality through effective testing, debugging, and maintenance is essential. This is especially the case as we acknowledge the prospects of negative…

Current interest in deep learning captures the attention of many programmers and researchers. Unfortunately, the lack of a unified schema for developing deep learning models results in methodological inconsistencies, unclear documentation,…

Methods to certify the robustness of neural networks in the presence of input uncertainty are vital in safety-critical settings. Most certification methods in the literature are designed for adversarial input uncertainty, but researchers…

Recent works have shown that deep neural networks can achieve super-human performance in a wide range of image classification tasks in the medical imaging domain. However, these works have primarily focused on classification accuracy,…

Quantum cryptography can provide a very high level of data security. However, a big challenge of this technique is errors in quantum channels. Therefore, error correction methods must be applied in real implementations. An example is error…

Analytical quality assurance, especially testing, is an integral part of software-intensive system development. With the increased usage of Artificial Intelligence (AI) and Machine Learning (ML) as part of such systems, this becomes more…

Prediction models based on deep neural networks are increasingly gaining attention for fast and accurate virtual screening systems. For decision makings in virtual screening, researchers find it useful to interpret an output of…

In the context of collaborative AI research and development projects, it would be ideal to have self-contained encapsulated algorithms that can be easily shared between different parties, executed and validated on data at different sites,…

We study the problem of creating strong, yet narrow, AI systems. While recent AI progress has been driven by the training of large general-purpose foundation models, the creation of smaller models specialized for narrow domains could be…

Traditional rule-based cybersecurity systems have proven highly effective against known malware threats. However, they face challenges in detecting novel threats. To address this issue, emerging cybersecurity systems are incorporating AI…

Neural network (NN) controllers achieve strong empirical performance on nonlinear dynamical systems, yet deploying them in safety-critical settings requires robustness to disturbances and uncertainty. We present a method for jointly…

A globally robust deep neural network resists perturbations on all meaningful inputs. Current robustness certification methods emphasize local robustness, struggling to scale and generalize. This paper presents a systematic and efficient…