用知识增强推理，让大模型同时满足欧盟AI法案合规与抗攻击需求。
Knowledge-Augmented Reasoning for EUAIA Compliance and Adversarial Robustness of LLMs
- 通过规则、保证案例和上下文映射构建推理层，连接法规与安全检测
- 实证表明该架构能同步提升模型在欧盟的合规性与对抗鲁棒性
- 适合需通过欧盟AI法案审计的大模型开发者与合规团队
欧盟人工智能法案（EUAIA）对AI系统提出了合规要求，这些要求与建立对抗鲁棒性的过程存在交集。然而，由于法规语言模糊且对抗攻击动态变化，使用大型语言模型（LLMs）的开发者可能面临重复劳动，且无法确信已达成合规或鲁棒性。本文提出一种功能架构，聚焦于弥合这两类属性的差距，引入具有明确来源的组件。基于文献推荐的检测层与法律要求的报告层，我们构建了一个基于知识增强（规则、保证案例、上下文映射）的推理层，旨在为开发者和审计员提供支持。研究结果表明，该方法为确保部署于欧盟的大模型同时具备合规性与对抗鲁棒性提供了新路径，从而支撑可信性。
原文摘要 · Abstract (English)
The EU AI Act (EUAIA) introduces requirements for AI systems which intersect with the processes required to establish adversarial robustness. However, given the ambiguous language of regulation and the dynamicity of adversarial attacks, developers of systems with highly complex models such as LLMs may find their effort to be duplicated without the assurance of having achieved either compliance or robustness. This paper presents a functional architecture that focuses on bridging the two properties, by introducing components with clear reference to their source. Taking the detection layer recommended by the literature, and the reporting layer required by the law, we aim to support developers and auditors with a reasoning layer based on knowledge augmentation (rules, assurance cases, contextual mappings). Our findings demonstrate a novel direction for ensuring LLMs deployed in the EU are both compliant and adversarially robust, which underpin trustworthiness.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。