# Safer Classification by Synthesis

arXiv: https://arxiv.org/abs/1711.08534 · HTML: https://mlsanity.com/paper/1711.08534/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Nov 2017.

## Built on by (most cited first, 8 of 8)

- [PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them](https://mlsanity.com/paper/2102.07033/) (2021)
- [How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review](https://mlsanity.com/paper/2107.12045/) (2021)
- [Bayesian OOD detection with aleatoric uncertainty and outlier exposure](https://mlsanity.com/paper/2102.12959/) (2021)
- [A Holistic Assessment of the Reliability of Machine Learning Systems](https://mlsanity.com/paper/2307.10586/) (2023)
- [A Novel Data Augmentation Technique for Out-of-Distribution Sample Detection using Compounded Corruptions](https://mlsanity.com/paper/2207.13916/) (2022)
- [When to Read Documents or QA History: On Unified and Selective Open-domain QA](https://mlsanity.com/paper/2306.04176/) (2023)
- [FROB: Few-shot ROBust Model for Classification and Out-of-Distribution Detection](https://mlsanity.com/paper/2111.15487/) (2021)
- [Use Classifier as Generator](https://mlsanity.com/paper/2209.09210/) (2022)

## Abstract (arXiv)

The discriminative approach to classification using deep neural networks has become the de-facto standard in various fields. Complementing recent reservations about safety against adversarial examples, we show that conventional discriminative methods can easily be fooled to provide incorrect labels with very high confidence to out of distribution examples. We posit that a generative approach is the natural remedy for this problem, and propose a method for classification using generative models. At training time, we learn a generative model for each class, while at test time, given an example to classify, we query each generator for its most similar generation, and select the class corresponding to the most similar one. Our approach is general and can be used with expressive models such as GANs and VAEs. At test time, our method accurately "knows when it does not know," and provides resilience to out of distribution examples while maintaining competitive performance for standard examples.