相关论文: Arguing from Hazard Analysis in Safety Cases: A Mo…

Inappropriate design and deployment of machine learning (ML) systems leads to negative downstream social and ethical impact -- described here as social and ethical risks -- for users, society and the environment. Despite the growing need to…

Embedding artificial intelligence into systems introduces significant challenges to modern engineering practices. Hazard analysis tools and processes have not yet been adequately adapted to the new paradigm. This paper describes initial…

We propose a novel approach to logic-based learning which generates assumption-based argumentation (ABA) frameworks from positive and negative examples, using a given background knowledge. These ABA frameworks can be mapped onto logic…

Model checking is a proven approach for checking whether the behavior model of a safety-critical system fulfills safety properties that are stated as LTL formulas.We propose rules for generating such LTL formulas automatically based on the…

Large Language Models (LLMs), such as GPT-3, have demonstrated remarkable natural language processing and generation capabilities and have been applied to a variety tasks, such as source code generation. This paper explores the potential of…

Following the rapid increase in Artificial Intelligence (AI) capabilities in recent years, the AI community has voiced concerns regarding possible safety risks. To support decision-making on the safe use and development of AI systems, there…

Modelling qualitative uncertainty in formal argumentation is essential both for practical applications and theoretical understanding. Yet, most of the existing works focus on \textit{abstract} models for arguing with uncertainty. Following…

We consider multi-agent argumentation, where each agent's view of the arguments is encoded as an argumentation framework (AF). Then we study deliberative processes than can occur on this basis. We think of a deliberative process as taking…

In this paper, we compose a new task for deep argumentative structure analysis that goes beyond shallow discourse structure analysis. The idea is that argumentative relations can reasonably be represented with a small set of predefined…

Debugging complex systems is a crucial yet time-consuming task. This paper presents the use of automata learning and testing techniques to obtain concise and informative bug descriptions. We introduce the concepts of Failure Explanations…

Large Language Model safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe. This classification proves insufficient when models encounter ethical dilemmas, where the capacity to reason…

Reasoning-based language models have demonstrated strong performance across various domains, with the most notable gains seen in mathematical and coding tasks. Recent research has shown that reasoning also offers significant benefits for…

Interpretability, trustworthiness, and usability are key considerations in high-stake security applications, especially when utilizing deep learning models. While these models are known for their high accuracy, they behave as black boxes in…

We present our Balanced, Integrated and Grounded (BIG) argument for assuring the safety of AI systems. The BIG argument adopts a whole-system approach to constructing a safety case for AI systems of varying capability, autonomy and…

We introduce SteeringSafety, a systematic framework for evaluating representation steering methods across seven safety perspectives spanning 17 datasets. While prior work highlights general capabilities of representation steering, we…

The notion of stability in a structured argumentation setup characterizes situations where the acceptance status associated with a given literal will not be impacted by any future evolution of this setup. In this paper, we abstract away…

Large Reasoning Models (LRMs) introduce a new generation paradigm of explicitly reasoning before answering, leading to remarkable improvements in complex tasks. However, they pose great safety risks against harmful queries and adversarial…

We present an empirical study aimed at analysing the use of viewpoints in an industrial Concurrent Engineering context. Our focus is on the viewpoints expressed in the argumentative process taking place in evaluation meetings. Our results…

Advances in machine learning have led to broad deployment of systems with impressive performance on important problems. Nonetheless, these systems can be induced to make errors on data that are surprisingly similar to examples the learned…

Identifying potential social and ethical risks in emerging machine learning (ML) models and their applications remains challenging. In this work, we applied two well-established safety engineering frameworks (FMEA, STPA) to a case study…