We introduce the novel concept of proof transfer for neural network verification. We show that by generating proof templates that capture and generalize existing proofs, we can speed up subsequent proofs. In particular we create these templates from previous proofs on the same neural network and consider two cases: (i) where the proofs are created online when verifying other properties and (ii) where the templates are created offline using a dataset. We base our methods on three key hypotheses of neural network robustness proofs. Our evaluation shows the potential of proof transfer for benefitting robustness verification of neural networks against adversarial patches, geometric, and $\ell_{\infty}$-perturbations.
翻译:我们引入神经网络核查的证据转让新概念。 我们显示,通过生成捕捉和普及现有证据的证明模板,我们可以加快随后的证明。 特别是,我们从同一神经网络上创建了以前证据的这些模板,并审议两个案例:(一) 当核查其他属性时,证据是在网上创建的,以及(二) 当使用数据集创建模板时,我们的方法基于神经网络可靠性证据的三个关键假设。我们的评估表明,证据转让有可能有利于神经网络对对抗性补丁、几何和$\ell ⁇ infty}-perubilation的稳健性核查。