An important pillar for safe machine learning (ML) is the systematic mitigation of weaknesses in neural networks to afford their deployment in critical applications. An ubiquitous class of safety risks are learned shortcuts, i.e. spurious correlations a network exploits for its decisions that have no semantic connection to the actual task. Networks relying on such shortcuts bear the risk of not generalizing well to unseen inputs. Explainability methods help to uncover such network vulnerabilities. However, many of these techniques are not directly applicable if access to the network is constrained, in so-called black-box setups. These setups are prevalent when using third-party ML components. To address this constraint, we present an approach to detect learned shortcuts using an interpretable-by-design network as a proxy to the black-box model of interest. Leveraging the proxy's guarantees on introspection we automatically extract candidates for learned shortcuts. Their transferability to the black box is validated in a systematic fashion. Concretely, as proxy model we choose a BagNet, which bases its decisions purely on local image patches. We demonstrate on the autonomous driving dataset A2D2 that extracted patch shortcuts significantly influence the black box model. By efficiently identifying such patch-based vulnerabilities, we contribute to safer ML models.
翻译:安全机器学习(ML)的一个重要支柱是系统地减少神经网络的弱点,以支付其在关键应用中的部署费用。无处不在的安全风险类别是学习的捷径,即:虚假的关联性,一个网络为其决定所利用的、与实际任务没有语义连接的网络所利用。依靠这些捷径的网络承担着不向无形输入推广的风险。解释性方法有助于发现这种网络的脆弱性。然而,如果在所谓的黑箱设置中进入网络受到限制,这些技术中有许多不能直接适用。在使用第三方 ML 组件时,这些设置很普遍。为了解决这一制约,我们提出了一个方法,用可解释的逐个设计网络来探测所学的捷径,以其作为替代黑箱模式的代名。利用这些捷径网络的保证,我们自动提取的近路口保证,我们用它来系统验证它们向黑盒的可转移性。具体地说,我们选择一个代理模式,在使用第三方 ML 模式时,这些设置这些设置是盛行的。为了解决这一制约,我们用一个办法,我们通过一个可解释的、可解释、可解释的网格的网路隔式的网路路路,我们通过这种安全地测量数据,我们用来测量的ML2 。我们用这种安全模式来测量的公交式的公交路路路。