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 2003.01155cs.SEcs.LG
收藏

基于概率的机器学习组件系统安全验证

Towards Probability-based Safety Verification of Systems with Components from Machine Learning

Hermann Kaindl, Stefan Kramer

摘要:

机器学习(ML)最近创造了许多新的成功故事。因此,在软件密集型系统(包括安全关键型系统)中使用ML技术的动机很强。这就提出了ML系统的安全验证问题,目前认为这是不可行的,或者至少是非常困难的。我们认为这需要考虑ML技术的特定属性,例如:(i)大多数ML方法都是归纳的,这既是它们的力量,也是它们的错误来源。(ii)由深度学习产生的神经网络(NN)在当前技术水平上是不透明的。因此,总会有错误残留,至少对于深度NN(DNN)来说,验证其内部结构是非常困难的。一般来说,安全工程不能完全保证不会发生任何伤害。这就是为什么使用概率,例如,用于指定风险或可容忍危险率(THR)。在这篇愿景论文中,我们提出了基于受控实验估计的错误概率和归纳学习分类器本身输出的错误概率进行验证。泛化误差界限可传播到危险的概率,其不得超过THR。因此,在安全关键系统中的ML组件的分类错误的概率上的定量确定的界限以明确定义的方式有助于后者的整体安全验证。

英文摘要:

Machine learning (ML) has recently created many new success stories. Hence, there is a strong motivation to use ML technology in software-intensive systems, including safety-critical systems. This raises the issue of safety verification of MLbased systems, which is currently thought to be infeasible or, at least, very hard. We think that it requires taking into account specific properties of ML technology such as: (i) Most ML approaches are inductive, which is both their power and their source of error. (ii) Neural networks (NN) resulting from deep learning are at the current state of the art not transparent. Consequently, there will always be errors remaining and, at least for deep NNs (DNNs), verification of their internal structure is extremely hard. In general, safety engineering cannot provide full guarantees that no harm will ever occur. That is why probabilities are used, e.g., for specifying a risk or a Tolerable Hazard Rate (THR). In this vision paper, we propose verification based on probabilities of errors both estimated by controlled experiments and output by the inductively learned classifier itself. Generalization error bounds may propagate to the probabilities of a hazard, which must not exceed a THR. As a result, the quantitatively determined bound on the probability of a classification error of an ML component in a safety-critical system contributes in a well-defined way to the latter's overall safety verification.

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。

↑