用控制理论提升LSTM抗干扰能力，给出恢复时间的理论保障。
Enhancing AI System Resiliency: Formulation and Guarantee for LSTM Resilience Based on Control Theory
- 基于δISS理论推导LSTM恢复时间的无数据上界
- 恢复时间上界可指导鲁棒训练，实测验证有效
- 适合安全关键场景的AI系统可靠性评估
本文提出一种新的理论框架，用于保证和评估控制系统中长短期记忆（LSTM）网络的韧性。引入“恢复时间”作为新韧性指标，量化LSTM在异常输入后恢复至正常状态所需时间。通过数学上改进增量输入-状态稳定性（δISS）理论，推导出适用于LSTM的数据无关恢复时间上界。该上界支持韧性感知训练。在简单模型上的实验验证了韧性估计与控制方法的有效性，为安全关键型AI应用的严格质量保障奠定了基础。
原文摘要 · Abstract (English)
This paper proposes a novel theoretical framework for guaranteeing and evaluating the resilience of long short-term memory (LSTM) networks in control systems. We introduce "recovery time" as a new metric of resilience in order to quantify the time required for an LSTM to return to its normal state after anomalous inputs. By mathematically refining incremental input-to-state stability ($δ$ISS) theory for LSTM, we derive a practical data-independent upper bound on recovery time. This upper bound gives us resilience-aware training. Experimental validation on simple models demonstrates the effectiveness of our resilience estimation and control methods, enhancing a foundation for rigorous quality assurance in safety-critical AI applications.
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。