arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.06576cs.LGcs.AIcs.CRcs.CV
收藏

用于寻找类编码模式的AI模型利用率测量

AI Model Utilization Measurements For Finding Class Encoding Patterns

National Institute of Standards Technology(美国国家标准与技术研究院)

Peter Bajcsy, Antonio Cardone, Chenyi Ling, Philippe Dessauw, Michael Majurski, Tim Blattner, Derek Juba, Walid Keyrouz

摘要:

这项工作解决了以下问题:(a)设计训练的人工智能(AI)模型的利用率测量,以及(b)解释如何根据这些测量在AI模型中编码训练数据。这些问题的原因是AI模型在安全和安全关键应用中缺乏可解释性,例如使用AI模型对自动驾驶汽车中的交通标志进行分类。我们通过引入人工智能模型利用率测量的理论基础和理解模式,在计算图(人工智能模型),子图和图节点的水平上对交通标志进行基于利用率的类编码来解决问题。从概念上讲,利用率是在AI模型的每个图节点(计算单元)上定义的,基于所有可能输出(张量状态)空间中唯一输出的数量和分布。在这项工作中,利用率测量是从AI模型中提取的,其中包括中毒和干净的AI模型。与干净的AI模型相比,中毒的AI模型是用包含系统的、物理上可实现的交通标志修改(即,触发器)在存在这样的触发器的情况下将正确的类标签改变为另一个标签。我们分析了这种干净和有毒的AI模型的类编码,并得出结论,对特洛伊木马注入和检测的影响。

英文摘要:

This work addresses the problems of (a) designing utilization measurements of trained artificial intelligence (AI) models and (b) explaining how training data are encoded in AI models based on those measurements. The problems are motivated by the lack of explainability of AI models in security and safety critical applications, such as the use of AI models for classification of traffic signs in self-driving cars. We approach the problems by introducing theoretical underpinnings of AI model utilization measurement and understanding patterns in utilization-based class encodings of traffic signs at the level of computation graphs (AI models), subgraphs, and graph nodes. Conceptually, utilization is defined at each graph node (computation unit) of an AI model based on the number and distribution of unique outputs in the space of all possible outputs (tensor-states). In this work, utilization measurements are extracted from AI models, which include poisoned and clean AI models. In contrast to clean AI models, the poisoned AI models were trained with traffic sign images containing systematic, physically realizable, traffic sign modifications (i.e., triggers) to change a correct class label to another label in a presence of such a trigger. We analyze class encodings of such clean and poisoned AI models, and conclude with implications for trojan injection and detection.

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。

↑