相关论文: Robust AI Security and Alignment: A Sisyphean Ende…

Every AI system is deployed by a human organization. In high risk applications, the combined human plus AI system must function as a high-reliability organization in order to avoid catastrophic errors. This short note reviews the properties…

The capabilities of artificial intelligence systems have been advancing to a great extent, but these systems still struggle with failure modes, vulnerabilities, and biases. In this paper, we study the current state of the field, and present…

The EU Artificial Intelligence Act (AIA) establishes different legal principles for different types of AI systems. While prior work has sought to clarify some of these principles, little attention has been paid to robustness and…

The AI alignment problem, which focusses on ensuring that artificial intelligence (AI), including AGI and ASI, systems act according to human values, presents profound challenges. With the progression from narrow AI to Artificial General…

This memorandum presents four recommendations aimed at strengthening the principles of AI model reliability and AI model governability, as DoW, ODNI, NIST, and CAISI refine AI assurance frameworks under the AI Action Plan. Our focus…

The issues of AI risk and AI safety are becoming critical as the prospect of artificial general intelligence (AGI) looms larger. The emergence of extremely large and capable generative models has led to alarming predictions and created a…

AI alignment research aims to develop techniques to ensure that AI systems do not cause harm. However, every alignment technique has failure modes, which are conditions in which there is a non-negligible chance that the technique fails to…

This vision paper presents initial research on assessing the robustness and reliability of AI-enabled systems, and key factors in ensuring their safety and effectiveness in practical applications, including a focus on accountability. By…

As artificial intelligence (AI) becomes deeply integrated into critical infrastructures and everyday life, ensuring its safe deployment is one of humanity's most urgent challenges. Current AI models prioritize task optimization over safety,…

The rapid advancement of AI has expanded its capabilities across domains, yet introduced critical technical vulnerabilities, such as algorithmic bias and adversarial sensitivity, that pose significant societal risks, including…

Artificial Intelligence (AI) is one of the most transformative technologies of the 21st century. The extent and scope of future AI capabilities remain a key uncertainty, with widespread disagreement on timelines and potential impacts. As…

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…

Alignment of artificial intelligence (AI) encompasses the normative problem of specifying how AI systems should act and the technical problem of ensuring AI systems comply with those specifications. To date, AI alignment has generally…

An impossibility theorem demonstrates that a particular problem or set of problems cannot be solved as described in the claim. Such theorems put limits on what is possible to do concerning artificial intelligence, especially the…

Artificial Intelligence (AI) is progressing rapidly, and companies are shifting their focus to developing generalist AI systems that can autonomously act and pursue goals. Increases in capabilities and autonomy may soon massively amplify…

As AI systems become more capable, widely deployed, and increasingly autonomous in critical areas such as cybersecurity, biological research, and healthcare, ensuring their safety and alignment with human values is paramount. Machine…

As the real-world impact of Artificial Intelligence (AI) systems has been steadily growing, so too have these systems come under increasing scrutiny. In response, the study of AI fairness has rapidly developed into a rich field of research…

AI is poised to revolutionize telecommunication networks by boosting efficiency, automation, and decision-making. However, the black-box nature of most AI models introduces substantial risk, possibly deterring adoption by network operators.…

The development of Artificial Intelligence (AI), including AI in Science (AIS), should be done following the principles of responsible AI. Progress in responsible AI is often quantified through evaluation metrics, yet there has been less…

In the rapidly evolving field of cybersecurity, ensuring the reproducibility of AI-driven research is critical to maintaining the reliability and integrity of security systems. This paper addresses the reproducibility crisis within the…