ForesightSafety Bench: A Frontier Risk Evaluation and Governance Framework towards Safe AI

TL;DR

The paper introduces ForesightSafety Bench, a comprehensive AI safety evaluation framework covering 94 risk dimensions, systematically assessing over twenty advanced models to identify safety vulnerabilities in frontier AI systems.

Contribution

It proposes a hierarchical, evolving safety benchmark with extensive risk dimensions and evaluates multiple large models to reveal key safety vulnerabilities in cutting-edge AI.

Findings

Widespread safety vulnerabilities across multiple AI safety pillars

Identification of key risk patterns and capability boundaries in advanced models

Benchmark covers 94 risk dimensions and includes extensive structured data

Abstract

Rapidly evolving AI exhibits increasingly strong autonomy and goal-directed capabilities, accompanied by derivative systemic risks that are more unpredictable, difficult to control, and potentially irreversible. However, current AI safety evaluation systems suffer from critical limitations such as restricted risk dimensions and failed frontier risk detection. The lagging safety benchmarks and alignment technologies can hardly address the complex challenges posed by cutting-edge AI models. To bridge this gap, we propose the "ForesightSafety Bench" AI Safety Evaluation Framework, beginning with 7 major Fundamental Safety pillars and progressively extends to advanced Embodied AI Safety, AI4Science Safety, Social and Environmental AI risks, Catastrophic and Existential Risks, as well as 8 critical industrial safety domains, forming a total of 94 refined risk dimensions. To date, the benchmark has accumulated tens of thousands of structured risk data points and assessment results, establishing a widely encompassing, hierarchically clear, and dynamically evolving AI safety evaluation framework. Based on this benchmark, we conduct systematic evaluation and in-depth analysis of over twenty mainstream advanced large models, identifying key risk patterns and their capability boundaries. The safety capability evaluation results reveals the widespread safety vulnerabilities of frontier AI across multiple pillars, particularly focusing on Risky Agentic Autonomy, AI4Science Safety, Embodied AI Safety, Social AI Safety and Catastrophic and Existential Risks. Our benchmark is released at https://github.com/Beijing-AISI/ForesightSafety-Bench. The project website is available at https://foresightsafety-bench.beijing-aisi.ac.cn/.