相关论文: Industrial AI Robustness Card for Time Series Mode…
Existing research on generative AI security is primarily driven by mutually reinforcing attack and defense methodologies grounded in empirical experience. This dynamic frequently gives rise to previously unknown attacks that can circumvent…
Assured AI in unrestricted settings is a critical problem. Our framework addresses AI assurance challenges lying at the intersection of domain adaptation, fairness, and counterfactuals analysis, operating via the discovery and intervention…
Due to the critical importance of Industrial Control Systems (ICS) to the operations of cities and countries, research into the security of critical infrastructure has become increasingly relevant and necessary. As a component of both the…
Detecting anomalies in temporal data has gained significant attention across various real-world applications, aiming to identify unusual events and mitigate potential hazards. In practice, situations often involve a mix of segment-level…
We demonstrate progress on the deployment of two sets of technologies to support distribution grid operators integrating high shares of renewable energy sources, based on a market for trading local energy flexibilities. An…
In August 2024, the EU Artificial Intelligence Act (AIA) came into force, marking the world's first large-scale regulatory framework for AI. Central to the AIA is a risk-based approach, aligning regulatory obligations with the potential…
This study offers an in-depth analysis of the application and implications of the National Institute of Standards and Technology's AI Risk Management Framework (NIST AI RMF) within the domain of surveillance technologies, particularly…
We tackle here a specific, still not widely addressed aspect, of AI robustness, which consists of seeking invariance / insensitivity of model performance to hidden factors of variations in the data. Towards this end, we employ a two step…
Artificial Intelligence (AI) has emerged as a transformative technology with the potential to revolutionize various sectors, from healthcare to finance, education, and beyond. However, successfully implementing AI systems remains a complex…
Industrial Control Systems (ICS) are often built from geographically distributed components and often use programmable logic controllers for localized processes. Since verification of such systems is challenging because of both time…
Healthcare AI holds the potential to increase patient safety, augment efficiency and improve patient outcomes, yet research is often limited by data access, cohort curation, and tooling for analysis. Collection and translation of electronic…
Continuous-time series is essential for different modern application areas, e.g. healthcare, automobile, energy, finance, Internet of things (IoT) and other related areas. Different application needs to process as well as analyse a massive…
The last decade has seen tremendous progress in AI technology and applications. With such widespread adoption, ensuring the reliability of the AI models is crucial. In past, we took the first step of creating a testing framework called…
Despite extensive research, time series classification and forecasting on noisy data remain highly challenging. The main difficulties lie in finding suitable mathematical concepts to describe time series and effectively separate noise from…
With the advancement of information retrieval (IR) technologies, robustness is increasingly attracting attention. When deploying technology into practice, we consider not only its average performance under normal conditions but, more…
Time Series Generation (TSG) has emerged as a pivotal technique in synthesizing data that accurately mirrors real-world time series, becoming indispensable in numerous applications. Despite significant advancements in TSG, its efficacy…
Autonomous systems increasingly rely on machine learning techniques to transform high-dimensional raw inputs into predictions that are then used for decision-making and control. However, it is often easy to maliciously manipulate such…
Monitoring fatigue is essential for improving safety, particularly for people who work long shifts or in high-demand workplaces. The development of wearable technologies, such as fitness trackers and smartwatches, has made it possible to…
Ensuring that AI systems reliably and robustly avoid harmful or dangerous behaviours is a crucial challenge, especially for AI systems with a high degree of autonomy and general intelligence, or systems used in safety-critical contexts. In…
AI policymakers are responsible for delivering effective governance mechanisms that can provide safe, aligned and trustworthy AI development. However, the information environment offered to policymakers is characterised by an unnecessarily…