arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.07560cs.CRcs.NI
收藏

学习APT杀链:基于溯源数据的时序推理用于攻击阶段估计

Learning the APT Kill Chain: Temporal Reasoning over Provenance Data for Attack Stage Estimation

Technische Universität Chemnitz(开姆尼茨工业大学)

Trung V. Phan, Thomas Bauschert

AI总结:

StageFinder通过融合溯源数据和时序学习,实现高精度的APT攻击阶段估计,宏F1分数达0.96,预测稳定性提升31%。

摘要:

高级持续性威胁(APT)通过多个阶段演变,每个阶段表现出不同的时间和结构行为。准确的阶段估计对于实现自适应网络防御至关重要。本文提出了StageFinder,一种用于从融合的主机和网络溯源数据中推断多阶段攻击进程的时序图学习框架。溯源图通过图神经网络编码,以捕捉进程、文件和连接之间的结构依赖关系,同时长短期记忆(LSTM)模型学习时间动态以估计与MITRE ATT&CK框架对齐的阶段概率。该模型在DARPA OpTC数据集上进行预训练,并在标记的DARPA透明计算数据上进行微调。实验结果表明,StageFinder在宏F1分数上达到0.96,并将预测波动性降低了31个百分点,与最先进的基线(Cyberian、NetGuardian)相比。这些结果突显了融合溯源和时间学习在准确且稳定的APT阶段推断中的有效性。

英文摘要:

Advanced Persistent Threats (APTs) evolve through multiple stages, each exhibiting distinct temporal and structural behaviors. Accurate stage estimation is critical for enabling adaptive cyber defense. This paper presents StageFinder, a temporal graph learning framework for multi-stage attack progression inference from fused host and network provenance data. Provenance graphs are encoded using a graph neural network to capture structural dependencies among processes, files, and connections, while a long short-term memory (LSTM) model learns temporal dynamics to estimate stage probabilities aligned with the MITRE ATT&CK framework. The model is pretrained on the DARPA OpTC dataset and fine-tuned on labeled DARPA Transparent Computing data. Experimental results demonstrate that StageFinder achieves a macro F1-score of 0.96 and reduces prediction volatility by 31 percent compared to state-of-the-art baselines (Cyberian, NetGuardian). These results highlight the effectiveness of fused provenance and temporal learning for accurate and stable APT stage inference.

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。

↑