Robustness Certification of Generative Models

Autor:	Mirman, Matthew, Gehr, Timon, Vechev, Martin
Rok vydání:	2020
Předmět:	Computer Science - Machine Learning Computer Science - Cryptography and Security Computer Science - Programming Languages Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Generative neural networks can be used to specify continuous transformations between images via latent-space interpolation. However, certifying that all images captured by the resulting path in the image manifold satisfy a given property can be very challenging. This is because this set is highly non-convex, thwarting existing scalable robustness analysis methods, which are often based on convex relaxations. We present ApproxLine, a scalable certification method that successfully verifies non-trivial specifications involving generative models and classifiers. ApproxLine can provide both sound deterministic and probabilistic guarantees, by capturing either infinite non-convex sets of neural network activation vectors or distributions over such sets. We show that ApproxLine is practically useful and can verify interesting interpolations in the networks latent space. Comment: Prior version submitted to ICLR 2020
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2004.14756 Zobrazit plný text záznamu View this record from Arxiv