# Learning Perceptually-Aligned Representations via Adversarial Robustness

@article{Engstrom2019LearningPR, title={Learning Perceptually-Aligned Representations via Adversarial Robustness}, author={L. Engstrom and Andrew Ilyas and Shibani Santurkar and D. Tsipras and B. Tran and A. Madry}, journal={ArXiv}, year={2019}, volume={abs/1906.00945} }

Many applications of machine learning require models that are human-aligned, i.e., that make decisions based on human-meaningful information about the input. We identify the pervasive brittleness of deep networks' learned representations as a fundamental barrier to attaining this goal. We then re-cast robust optimization as a tool for enforcing human priors on the features learned by deep neural networks. The resulting robust feature representations turn out to be significantly more aligned… CONTINUE READING

#### Supplemental Code

GITHUB REPO

Via Papers with Code

A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.

#### Paper Mentions

32 Citations

Decoder-free Robustness Disentanglement without (Additional) Supervision

- Mathematics, Computer Science
- 2020

Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization

- Computer Science, Mathematics
- 2020

Fast Training of Deep Neural Networks Robust to Adversarial Perturbations

- Computer Science, Mathematics
- 2020

Improving sample diversity of a pre-trained, class-conditional GAN by changing its class embeddings

- Mathematics, Computer Science
- 2019

#### References

##### Publications referenced by this paper.

SHOWING 1-10 OF 49 REFERENCES

Large Scale GAN Training for High Fidelity Natural Image Synthesis

- Mathematics, Computer Science
- 2019

1117

DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

- Computer Science
- 2014

3496

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

- Computer Science, Mathematics
- 2016

6360