Related papers: ForesightSafety Bench: A Frontier Risk Evaluation …
Recent advances in Large Language Models (LLMs) have sparked concerns over their potential to acquire and misuse dangerous or high-risk capabilities, posing frontier risks. Current safety evaluations primarily test for what a model…
When AI interacts with the physical world -- as a robot or an assistive agent -- new safety challenges emerge beyond those of purely ``digital AI". In such interactions, the potential for physical harm is direct and immediate. How well do…
The impact of frontier AI (i.e., AI agents and foundation models) in cybersecurity is rapidly increasing. In this paper, we comprehensively analyze this trend through multiple aspects: quantitative benchmarks, qualitative literature review,…
The rapid diffusion of agentic AI has created a new coverage problem for commercial insurance: some AI-mediated losses are now affirmatively insured, some create silent-AI exposure under legacy cyber, technology errors-and-omissions (E&O),…
Recent discussions and research in AI safety have increasingly emphasized the deep connection between AI safety and existential risk from advanced AI systems, suggesting that work on AI safety necessarily entails serious consideration of…
As AI models are increasingly deployed across diverse real-world scenarios, ensuring their safety remains a critical yet underexplored challenge. While substantial efforts have been made to evaluate and enhance AI safety, the lack of a…
AI models are increasingly prevalent in high-stakes environments, necessitating thorough assessment of their capabilities and risks. Benchmarks are popular for measuring these attributes and for comparing model performance, tracking…
Cybersecurity spans multiple interconnected domains, complicating the development of meaningful, labor-relevant benchmarks. Existing benchmarks assess isolated skills rather than integrated performance. We find that pre-trained knowledge of…
This chapter introduces a conceptual framework for qualitative risk assessment of AI, particularly in the context of the EU AI Act. The framework addresses the complexities of legal compliance and fundamental rights protection by itegrating…
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…
Although general-purpose AI systems offer transformational opportunities in science and industry, they simultaneously raise critical concerns about safety, misuse, and potential loss of control. Despite these risks, methods for assessing…
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…
This paper introduces v0.5 of the AI Safety Benchmark, which has been created by the MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to assess the safety risks of AI systems that use chat-tuned language models.…
Frontier AI systems are increasingly capable and deployed in high-stakes multi-agent environments. However, existing AI safety benchmarks largely evaluate single agents, leaving multi-agent risks such as coordination failure and conflict…
As AI rapidly advances, the security risks posed by AI are becoming increasingly severe, especially in critical scenarios, including those posing existential risks. If AI becomes uncontrollable, manipulated, or actively evades safety…
Frontier artificial intelligence (AI) systems pose increasing risks to society, making it essential for developers to provide assurances about their safety. One approach to offering such assurances is through a safety case: a structured,…
Although discourse around the risks of Artificial Intelligence (AI) has grown, it often lacks a comprehensive, multidimensional framework, and concrete causal pathways mapping hazard to harm. This paper aims to bridge this gap by examining…
The rapid deployment of LLM-based autonomous agents has introduced safety risks that extend far beyond traditional LLM concerns, prompting a proliferation of safety benchmarks since late 2023. However, these benchmarks have developed…
This year, jurisdictions worldwide, including the United States, the European Union, the United Kingdom, and China, are set to enact or revise laws governing frontier AI. Their efforts largely rely on the assumption that increasing model…
AI character platforms, which allow users to engage in conversations with AI personas, are a rapidly growing application domain. However, their immersive and personalized nature, combined with technical vulnerabilities, raises significant…