STARS:基于技能触发的请求条件调用安全性审计
STARS: Skill-Triggered Audit for Request-Conditioned Invocation Safety in Agent Systems
AI总结:
STARS通过结合静态能力先验、请求条件调用风险模型和校准风险融合策略,提升代理系统调用时的风险评估与优先级排序能力,优于静态筛查和上下文评分方法。
摘要:
自主语言模型代理越来越多地依赖可安装技能和工具来完成用户任务。静态技能审计可以在部署前暴露能力表面,但无法确定特定调用在当前用户请求和运行时上下文下的安全性。因此,我们研究技能调用审计作为持续风险估计问题:给定用户请求、候选技能和运行时上下文,预测一个分数以支持排序和优先级排序,在硬干预应用之前。我们引入STARS,结合静态能力先验、请求条件调用风险模型和校准风险融合策略。为了评估此设置,我们构建了SIA-Bench,包含3000条调用记录的基准,具有组安全拆分、行踪元数据、运行时上下文、标准操作标签和衍生的连续风险目标。在间接提示注入攻击的留出拆分上,校准融合达到0.439高风险AUPRC,优于上下文评分器的0.405和最强静态基线的0.380,而上下文评分器仍保持更好的校准(预期校准误差0.289)。在锁定的分布测试拆分上,收益较小,静态先验仍具价值。因此得出的结论更为狭窄:请求条件审计在调用时的风险评分和优先级排序层最为有价值,而非替代静态筛查。代码可在https://github.com/123zgj123/STARS获取。
英文摘要:
Autonomous language-model agents increasingly rely on installable skills and tools to complete user tasks. Static skill auditing can expose capability surface before deployment, but it cannot determine whether a particular invocation is unsafe under the current user request and runtime context. We therefore study skill invocation auditing as a continuous-risk estimation problem: given a user request, candidate skill, and runtime context, predict a score that supports ranking and triage before a hard intervention is applied. We introduce STARS, which combines a static capability prior, a request-conditioned invocation risk model, and a calibrated risk-fusion policy. To evaluate this setting, we construct SIA-Bench, a benchmark of 3,000 invocation records with group-safe splits, lineage metadata, runtime context, canonical action labels, and derived continuous-risk targets. On a held-out split of indirect prompt injection attacks, calibrated fusion reaches 0.439 high-risk AUPRC, improving over 0.405 for the contextual scorer and 0.380 for the strongest static baseline, while the contextual scorer remains better calibrated with 0.289 expected calibration error. On the locked in-distribution test split, gains are smaller and static priors remain useful. The resulting claim is therefore narrower: request-conditioned auditing is most valuable as an invocation-time risk-scoring and triage layer rather than as a replacement for static screening. Code is available at https://github.com/123zgj123/STARS.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。