通过计算图模式识别模型家族，97%准确率自动追溯模型血统。
ShadowGenes: Leveraging Recurring Patterns within Computational Graphs for Model Genealogy
- 构建模型计算图，提取内部操作的重复模式作为签名
- 在1400+模型上达到97.49%召回率与99.51%精确率
- 无需外部信息，适合模型溯源与安全检测
机器学习模型血缘关系有助于确定神经网络所属的架构族。本文提出ShadowGenes，一种基于签名的新型方法，用于识别模型的架构、类型及家族归属。该方法构建与序列化格式无关的计算图，分析其内部操作以识别独特模式，并据此构建与优化签名。我们展示了签名构建与模型扫描的具体流程。此方法可直接应用于模型文件，无需额外外部信息。我们在包含超过1,400个模型的标注数据集上测试，实现平均真阳性率为97.49%，精确率为99.51%，验证了该技术在模型血缘追踪中的实用性。该能力使从业者能理解模型使用场景、内部计算过程，并识别潜在安全风险，如模型后门。
原文摘要 · Abstract (English)
Machine learning model genealogy enables practitioners to determine which architectural family a neural network belongs to. In this paper, we introduce ShadowGenes, a novel, signature-based method for identifying a given model's architecture, type, and family. Our method involves building a computational graph of the model that is agnostic of its serialization format, then analyzing its internal operations to identify unique patterns, and finally building and refining signatures based on these. We highlight important workings of the underlying engine and demonstrate the technique used to construct a signature and scan a given model. This approach to model genealogy can be applied to model files without the need for additional external information. We test ShadowGenes on a labeled dataset of over 1,400 models and achieve a mean true positive rate of 97.49% and a precision score of 99.51%; which validates the technique as a practical method for model genealogy. This enables practitioners to understand the use cases of a given model, the internal computational process, and identify possible security risks, such as the potential for model backdooring.
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。