通过可执行安全规则蕴含实现视觉合规
Visual Compliance via Executable Safety Rule Entailment
浏览论文内容
中文总结 AI 辅助
提出GuardEn可执行防护框架，通过安全规则编译和场景接地执行实现复杂视觉安全规则的可解释推理，在SafetyVisionBench上平均提升9.8个F1点。
中文摘要 AI 辅助
大型语言模型和视觉语言模型的最新进展使安全系统能够超越简单的风险模式，推理更情境化和语义化的安全问题。然而，随着风险模式不断演变和安全规则日益复杂，现有的基于训练的端到端防护措施在适应性和对复杂安全规则的可解释推理方面面临持续挑战。为解决这些挑战，我们提出了GuardEn（通过安全规则蕴含进行防护），一种可执行的防护框架，通过安全规则编译将安全策略分解为原子命题，并将其组合建模为可执行代码。在测试时，场景接地执行利用从场景图中提取的情境视觉信息实例化这些原子命题，实现基于规则且可解释的安全推理。在SafetyVisionBench上的实验证明了可编程防护在复杂视觉安全评估中的有效性，相比最强基线平均提高了9.8个F1分数点。
英文摘要
Recent advances in LLMs and VLMs have enabled safety systems to reason beyond simple risk patterns toward more contextual and semantic safety concerns. However, as risk patterns continue to evolve and safety rules become more complex, existing training-based end-to-end safeguards face persistent challenges in adaptability and explainable reasoning over complex safety rules. To address these challenges, we propose GuardEn (Guarding by Safety Rule Entailment), an executable safeguard framework that decomposes safety policies into atomic propositions through Safety-Rule Compilation, modeling their composition as executable code. At test time, Scene-Grounded Execution instantiates these atomic propositions with contextual visual information derived from scene graphs, enabling rule-grounded and interpretable safety reasoning. Experiments on SafetyVisionBench demonstrate the effectiveness of programmable safeguard for complex visual safety assessment, achieving an average improvement of 9.8 F1 points over the strongest baseline.
发表机构
- Sungkyunkwan University（成均馆大学）
机构由 AI 辅助整理，请以论文原文为准。
