Related papers: Assessing confidence in frontier AI safety cases

This paper presents an approach to developing assurance cases for adversarial robustness and regulatory compliance in large language models (LLMs). Focusing on both natural and code language tasks, we explore the vulnerabilities these…

Assurance cases provide an organized and explicit argument for correctness. They can dramatically improve the certification of Scientific Computing Software (SCS). Assurance cases have already been effectively used for safety cases for real…

In recent years the use of Artificial Intelligence (AI) has become increasingly prevalent in a growing number of fields. As AI systems are being adopted in more high-stakes areas such as medicine and finance, ensuring that they are…

The integration of Artificial Intelligence (AI) into safety-critical systems introduces a new reliability paradigm: silent failures, where AI produces confident but incorrect outputs that can be dangerous. This paper introduces the Formal…

The integration of AI into radiology introduces opportunities for improved clinical care provision and efficiency but it demands a meticulous approach to mitigate potential risks as with any other new technology. Beginning with rigorous…

This article argues that frontier artificial intelligence (AI) developers need an internal audit function. First, it describes the role of internal audit in corporate governance: internal audit evaluates the adequacy and effectiveness of a…

The success and wide adoption of generative AI (GenAI), particularly large language models (LLMs), has attracted the attention of cybercriminals seeking to abuse models, steal sensitive data, or disrupt services. Moreover, providing…

There is an increasing adoption of artificial intelligence in safety-critical applications, yet practical schemes for certifying that AI systems are safe, lawful and socially acceptable remain scarce. This white paper presents the T\"UV…

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…

As artificial intelligence (AI), including machine learning (ML) models and foundation models (FMs), is increasingly deployed in high-stakes domains, ensuring their trustworthiness has become a central challenge. However, the core…

As AI systems become integral to critical operations across industries and services, ensuring their reliability and safety is essential. We offer a framework that integrates established reliability and resilience engineering principles into…

Artificial Intelligence brings innovations into the society. However, bias and unethical exist in many algorithms that make the applications less trustworthy. Threats hunting algorithms based on machine learning have shown great advantage…

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…

AI agents have been boosted by large language models. AI agents can function as intelligent assistants and complete tasks on behalf of their users with access to tools and the ability to execute commands in their environments. Through…

To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, this report presents a comprehensive assessment of their frontier risks. Drawing on the E-T-C analysis (deployment…

Safety alignment is an essential research topic for real-world AI applications. Despite the multifaceted nature of safety and trustworthiness in AI, current safety alignment methods often focus on a comprehensive notion of safety. By…

In the ever-expanding landscape of Artificial Intelligence (AI), where innovation thrives and new products and services are continuously being delivered, ensuring that AI systems are designed and developed responsibly throughout their…

Explainable AI (XAI) holds significant promise for enhancing the transparency and trustworthiness of AI-driven threat detection in Security Operations Centers (SOCs). However, identifying the appropriate level and format of explanation,…

The A2AS framework is introduced as a security layer for AI agents and LLM-powered applications, similar to how HTTPS secures HTTP. A2AS enforces certified behavior, activates model self-defense, and ensures context window integrity. It…

To facilitate the widespread acceptance of AI systems guiding decision-making in real-world applications, it is key that solutions comprise trustworthy, integrated human-AI systems. Not only in safety-critical applications such as…