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 2110.01232cs.AI
收藏

基于机器学习的图像分类器安全性基准测试

Benchmarking Safety Monitors for Image Classifiers with Machine Learning

LAAS-CNRS(法国国家科学研究中心实验室分析与建筑系统实验室);University of Toulouse(图卢兹大学)

Raul Sena Ferreira, Jean Arlat, Jeremie Guiochet, Hélène Waeselynck

摘要:

高精度的机器学习(ML)图像分类器不能保证它们在操作时不会失败。因此,它们在安全关键应用(如自动驾驶汽车)中的部署仍然是一个悬而未决的问题。使用容错机制,如安全监视器是一个有前途的方向,以保持系统在一个安全的状态,尽管错误的ML分类器。由于机器学习的预测是直接影响安全的核心信息,因此许多工作都集中在监测机器学习模型本身。因此,在安全关键应用的背景下检查这种监视器的效率是一个重大的挑战。因此,本文旨在建立一个基准框架,用于ML图像分类器的基准监测。此外,我们提出了一个框架,涵盖了整个管道,从数据生成到评估。我们的方法措施监测性能与一组更广泛的指标比通常在文献中提出。此外,我们在79个基准数据集中对三种不同的监控方法进行了基准测试,这些数据集包含五类图像分类器的分布外数据:类新颖性,噪声,异常,分布偏移和对抗攻击。我们的研究结果表明,这些监测器并不比随机监测器更准确。我们还发布了所有实验的代码,以确保重复性。

英文摘要:

High-accurate machine learning (ML) image classifiers cannot guarantee that they will not fail at operation. Thus, their deployment in safety-critical applications such as autonomous vehicles is still an open issue. The use of fault tolerance mechanisms such as safety monitors is a promising direction to keep the system in a safe state despite errors of the ML classifier. As the prediction from the ML is the core information directly impacting safety, many works are focusing on monitoring the ML model itself. Checking the efficiency of such monitors in the context of safety-critical applications is thus a significant challenge. Therefore, this paper aims at establishing a baseline framework for benchmarking monitors for ML image classifiers. Furthermore, we propose a framework covering the entire pipeline, from data generation to evaluation. Our approach measures monitor performance with a broader set of metrics than usually proposed in the literature. Moreover, we benchmark three different monitor approaches in 79 benchmark datasets containing five categories of out-of-distribution data for image classifiers: class novelty, noise, anomalies, distributional shifts, and adversarial attacks. Our results indicate that these monitors are no more accurate than a random monitor. We also release the code of all experiments for reproducibility.

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。

↑