相关论文: Architecting Safer Autonomous Aviation Systems
AI safety benchmarks are pivotal for safety in advanced AI systems; however, they have significant technical, epistemic, and sociotechnical shortcomings. We present a review of 210 safety benchmarks that maps out common challenges in safety…
The increasing popularity of deep learning models has created new opportunities for developing AI-based recommender systems. Designing recommender systems using deep neural networks requires careful architecture design, and further…
Software requirements expressed in natural language (NL) frequently suffer from verbosity, ambiguity, and inconsistency. This creates a range of challenges, including selecting an appropriate architecture for a system and assessing…
AI agents, specifically powered by large language models, have demonstrated exceptional capabilities in various applications where precision and efficacy are necessary. However, these agents come with inherent risks, including the potential…
Concerns around future dangers from advanced AI often centre on systems hypothesised to have intrinsic characteristics such as agent-like behaviour, strategic awareness, and long-range planning. We label this cluster of characteristics as…
Context. Developing secure and reliable software remains a key challenge in software engineering (SE). The ever-evolving technological landscape offers both opportunities and threats, creating a dynamic space where chaos and order compete.…
The adoption of machine learning (ML) components in software systems raises new engineering challenges. In particular, the inherent uncertainty regarding functional suitability and the operation environment makes architecture evaluation and…
The integration of Autonomous Weapon Systems (AWS) into military operations presents both significant opportunities and challenges. This paper explores the multifaceted nature of trust in AWS, emphasising the necessity of establishing…
As AI technologies increase in capability and ubiquity, AI accidents are becoming more common. Based on normal accident theory, high reliability theory, and open systems theory, we create a framework for understanding the risks associated…
Software architecture decision-making is critical to the success of a software system as software architecture sets the structure of the system, determines its qualities, and has far-reaching consequences throughout the system life cycle.…
The increased adoption of Artificial Intelligence (AI) presents an opportunity to solve many socio-economic and environmental challenges; however, this cannot happen without securing AI-enabled technologies. In recent years, most AI models…
The prediction quality of machine learnt models and the functionality they ultimately enable (e.g., object detection), is typically evaluated using a variety of quantitative metrics that are specified in the associated model performance…
A large body of research in continual learning is devoted to overcoming the catastrophic forgetting of neural networks by designing new algorithms that are robust to the distribution shifts. However, the majority of these works are strictly…
With artificial intelligence (AI) being applied to bring autonomy to decision-making in safety-critical domains such as the ones typified in the aerospace and emergency-response services, there has been a call to address the ethical…
Software architecture related issues are important for robotic systems. Architecture centric development and evolution of software for robotic systems has been attracting researchers attention for more than two decades. The objective of…
Architecture evaluation methods have been extensively used to evaluate software designs. Several evaluation methods have been proposed to analyze tradeoffs between different quality attributes. Also, having competing qualities leads to…
As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…
Threat modeling is a popular method to securely develop systems by achieving awareness of potential areas of future damage caused by adversaries. However, threat modeling for systems relying on Artificial Intelligence is still not well…
There is a growing proliferation of AI systems designed to mimic people's behavior, work, abilities, likenesses, or humanness -- systems we dub AI automatons. Individuals, groups, or generic humans are being simulated to produce creative…
This work aims to show the applicability, and how, of privacy by design approach to biometric systems and the benefit of using formal methods to this end. Starting from a general framework that has been introduced at STM in 2014, that…