arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2205.07736cs.SEcs.LG
收藏

基于符号串操作的OoD检测器角点优先级排序

Prioritizing Corners in OoD Detectors via Symbolic String Manipulation

Fraunhofer IKS(弗劳恩霍夫认知系统研究所);Univ. Grenoble Alpes(格勒诺布尔阿尔卑斯大学)

Chih-Hong Cheng, Changshun Wu, Emmanouil Seferis, Saddek Bensalem

摘要:

为了保证深度神经网络(DNN)的安全性,分布外(OoD)监控技术是必不可少的,因为它们过滤了远离训练数据集的虚假输入。本文研究了系统地测试OoD监视器的问题,以避免输入数据点被监视器测试为分布内,但DNN产生虚假输出预测的情况。我们考虑的定义,“分布”的特征在于在特征空间中的一个联盟的超矩形从训练数据集学习。因此,测试被简化为在特征空间中寻找远离可用训练数据的超矩形中的角。具体地说,我们将每个数据点的抽象位置编码为有限长度的二进制字符串,并使用二进制决策图(BDD)将所有二进制字符串的并集压缩存储。我们演示了如何使用BDD象征性地提取远离训练集中所有数据点的角点。除了测试用例生成之外,我们还解释了如何使用建议的角点来微调DNN,以确保它不会过度自信地预测。结果进行评估的例子,如数字和交通标志识别。

英文摘要:

For safety assurance of deep neural networks (DNNs), out-of-distribution (OoD) monitoring techniques are essential as they filter spurious input that is distant from the training dataset. This paper studies the problem of systematically testing OoD monitors to avoid cases where an input data point is tested as in-distribution by the monitor, but the DNN produces spurious output predictions. We consider the definition of "in-distribution" characterized in the feature space by a union of hyperrectangles learned from the training dataset. Thus the testing is reduced to finding corners in hyperrectangles distant from the available training data in the feature space. Concretely, we encode the abstract location of every data point as a finite-length binary string, and the union of all binary strings is stored compactly using binary decision diagrams (BDDs). We demonstrate how to use BDDs to symbolically extract corners distant from all data points within the training set. Apart from test case generation, we explain how to use the proposed corners to fine-tune the DNN to ensure that it does not predict overly confidently. The result is evaluated over examples such as number and traffic sign recognition.

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。

↑