Paper Info
Title
E-ABS: Extending the Analysis-By-Synthesis Robust Classification Model to More Complex Image Domains
Abstract
ABSTRACTConditional generative models, such as Schott et al.'s Analysis-by-Synthesis (ABS), have state-of-the-art robustness on MNIST, but fail in more challenging datasets. In this paper, we present E-ABS, an improvement on ABS that achieves state-of-the-art robustness on SVHN. E-ABS gives more reliable class-conditional likelihood estimations on both in-distribution and out-of-distribution samples than ABS. Theoretically, E-ABS preserves ABS's key features for robustness; thus, we show that E-ABS has similar certified robustness as ABS. Empirically, E-ABS outperforms both ABS and adversarial training on SVHN and a traffic sign dataset, achieving state-of-the-art robustness on these two real-world tasks. Our work shows a connection between ABS-like models and some recent advances on generative models, suggesting that ABS-like models are a promising direction for defending adversarial examples.
Year
DOI
Venue
2020
10.1145/3411508.3421382
CCS
Keywords
DocType
Citations 
Computer science,Pattern recognition,Speech coding,Artificial intelligence
Conference
0
PageRank 
References 
Authors
0.34
0
2
Name
Order
Citations
PageRank
An Ju1123.72
David Wagner212563933.74