Harmonizing AI Safety Thresholds
Frontier AI companies have published capability thresholds that differ substantially, making it difficult for third parties to verify whether a threshold has been crossed or to compare requirements across companies. Moreover, without common minimum thresholds, risk mitigation may be inconsistent, creating a potential race to the bottom in safety standards. We develop a methodology for deriving harmonized thresholds across three risk domains. For misuse risks (cyber and biological), we take expected harm as the key primitive and use an explicit risk-modeling approach that accounts for risk channels and model release conditions. For automated AI R&D, we base our proposed threshold on the observed rate of AI progress rather than expected harm. Our analysis expands upon prior work and highlights existing empirical gaps and limitations.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Reinterpreting Safety Thresholds as Neuron Spiking Thresholds
Surrogate Safety Measures (SSMs) are extensively utilised in the evaluation of traffic risk in automated driving contexts. However, the majority of SSM-based evaluations employ fixed thresholds that fail to capture the h…
Multi-Objective Value Iteration with Parameterized Threshold-Based Safety Constraints
We consider an environment with multiple reward functions. One of them represents goal achievement and the others represent instantaneous safety conditions. We consider a scenario where the safety rewards should always b…
Ensuring Safety in an Uncertain Environment: Constrained MDPs via Stochastic Thresholds
This paper studies constrained Markov decision processes (CMDPs) with constraints against stochastic thresholds, aiming at the safety of reinforcement learning in unknown and uncertain environments. We leverage a Growing…
reinforcement-learningReinforcement LearningThe Biosecurity Blind Spot: Systematic Dual-use Detection in Open Science Infrastructure
AI is transforming life sciences research at unprecedented speed, accelerating discovery across protein structure prediction, genome modeling, and drug development (Jumper et al., 2021; Mak et al., 2024). Yet this rapid …
Protein Structure PredictionTwo Birds, One Projection: Harmonizing Safety and Utility in LVLMs via Inference-time Feature Projection
Existing jailbreak defence frameworks for Large Vision-Language Models often suffer from a safety utility tradeoff, where strengthening safety inadvertently degrades performance on general visual-grounded reasoning tasks…