Antares：用于智能体漏洞定位的基础模型
Antares: Foundation Models for Agentic Vulnerability Localization
浏览论文内容
中文总结 AI 辅助
该研究提出基于IBM Granite的Antares系列紧凑语言模型，经两阶段训练用于智能体漏洞定位，其30亿参数版本性能接近GPT-5.5且远超更大模型，推理高效低成本。
中文摘要 AI 辅助
漏洞定位是软件安全的基础步骤，要求模型对大型代码库进行推理并迭代识别易受攻击的实现。我们提出Antares，这是一系列紧凑的语言模型（3.5亿、10亿和30亿参数），用于智能体漏洞定位。Antares基于IBM Granite基础模型，通过两阶段流程训练，结合网络安全推理和仓库探索数据的监督微调，以及对易受攻击仓库的可验证奖励的强化学习。在广泛评估中，Antares-3B接近GPT-5.5，同时在性能上超过规模大200倍以上的开放权重模型。Antares系列还支持快速、低成本的本地推理，在单个H100 GPU上完成500项任务的完整评估扫描约需15分钟，对应每项任务的摊销评估时间不足2秒，成本低于0.002美元。
英文摘要
Vulnerability localization is a fundamental step in software security, requiring models to reason over large codebases and iteratively identify vulnerable implementations. We present Antares, a family of compact language models (350M, 1B, and 3B parameters) for agentic vulnerability localization. Based on IBM Granite base models, Antares is trained through a two-stage pipeline that combines supervised fine-tuning on cybersecurity reasoning and repository exploration data with reinforcement learning from verifiable rewards over vulnerable repositories. Across extensive evaluations, Antares-3B approaches GPT-5.5 while outperforming open-weight models over 200x larger in size. The Antares family further enables fast, low-cost local inference, completing a full 500-task evaluation sweep in approximately 15 minutes on a single H100 GPU, corresponding to an amortized evaluation time of under 2 seconds and less than $0.002 per task.
发表机构
- Foundation AI–Cisco Systems Inc.（Foundation AI–思科公司）
- Yale University（耶鲁大学）
机构由 AI 辅助整理，请以论文原文为准。
