Related papers: Quantifying AI Vulnerabilities: A Synthesis of Com…

This paper reviews Trustworthy Artificial Intelligence (TAI) and its various definitions. Considering the principles respected in any society, TAI is often characterized by a few attributes, some of which have led to confusion in regulatory…

An AI design framework was developed based on three core principles, namely understandability, trust, and usability. The framework was conceptualized by synthesizing evidence from the literature and by consulting with experts. The initial…

We introduce the AI Security Pyramid of Pain, a framework that adapts the cybersecurity Pyramid of Pain to categorize and prioritize AI-specific threats. This framework provides a structured approach to understanding and addressing various…

Artificial Intelligence (AI) systems, trained in controlled environments, often struggle in real-world complexities. We propose a general framework for estimating domain complexity across diverse environments, like open-world learning and…

The remarkable achievements of Artificial Intelligence (AI) algorithms, particularly in Machine Learning (ML) and Deep Learning (DL), have fueled their extensive deployment across multiple sectors, including Software Engineering (SE).…

There is an increasing imperative to anticipate and understand the performance and safety of generative AI systems in real-world deployment contexts. However, the current evaluation ecosystem is insufficient: Commonly used static benchmarks…

Powerful new frontier AI technologies are bringing many benefits to society but at the same time bring new risks. AI developers and regulators are therefore seeking ways to assure the safety of such systems, and one promising method under…

Artificial Intelligence (AI) systems are increasingly prominent in emerging smart cities, yet their reliability remains a critical concern. These systems typically operate through a sequence of interconnected functional stages, where…

The field of Artificial Intelligence (AI) and, in particular, the Machine Learning area, counts on a wide range of performance metrics and benchmark data sets to assess the problem-solving effectiveness of its solutions. However, the…

Artificial intelligence (AI) is a powerful tool for reshaping healthcare systems. In healthcare, AI is invaluable for its capacity to manage vast amounts of data, which can lead to more accurate and speedy diagnoses, ultimately easing the…

Our survey of 53 specialists across 105 AI reliability and security research areas identifies the most promising research prospects to guide strategic AI R&D investment. As companies are seeking to develop AI systems with broadly…

The rapid rise of autonomous AI systems and advancements in agent capabilities are introducing new risks due to reduced oversight of real-world interactions. Yet agent testing remains nascent and is still a developing science. As AI agents…

The remarkable advancements in artificial intelligence (AI), primarily driven by deep neural networks, have significantly impacted various aspects of our lives. However, the current challenges surrounding unsustainable computational…

In the rapidly evolving field of artificial intelligence (AI), the identification, documentation, and mitigation of vulnerabilities are paramount to ensuring robust and secure systems. This paper discusses the minimum elements for AI…

Modern general-purpose artificial intelligence (AI) systems present an urgent risk management challenge, as their rapidly evolving capabilities and potential for catastrophic harm outpace our ability to reliably assess their risks. Current…

Agentic AI systems powered by large language models (LLMs) and endowed with planning, tool use, memory, and autonomy, are emerging as powerful, flexible platforms for automation. Their ability to autonomously execute tasks across web,…

Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in various domains. While these advancements promise significant…

Although AI systems have been applied in various fields and achieved impressive performance, their safety and reliability are still a big concern. This is especially important for safety-critical tasks. One shared characteristic of these…

Safety and responsibility evaluations of advanced AI models are a critical but developing field of research and practice. In the development of Google DeepMind's advanced AI models, we innovated on and applied a broad set of approaches to…

Safety cases, structured arguments that a system is acceptably safe, are becoming central to the governance of AI systems. Yet, traditional safety-case practices from aviation or nuclear engineering rely on well-specified system boundaries,…