Gödel's Sentence Is An Adversarial Example But Unsolvable
arXiv:2002.10703
Abstract
In recent years, different types of adversarial examples from different fields have emerged endlessly, including purely natural ones without perturbations. A variety of defenses are proposed and then broken quickly. Two fundamental questions need to be asked: What's the reason for the existence of adversarial examples and are adversarial examples unsolvable? In this paper, we will show the reason for the existence of adversarial examples is there are non-isomorphic natural explanations that can all explain data set. Specifically, for two natural explanations of being true and provable, Gödel's sentence is an adversarial example but ineliminable. It can't be solved by the re-accumulation of data set or the re-improvement of learning algorithm. Finally, from the perspective of computability, we will prove the incomputability for adversarial examples, which are unrecognizable.
References in corpus (7)
- Towards Deep Neural Network Architectures Robust to Adversarial Examples
- Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey
- Towards Crafting Text Adversarial Samples
- Adversarial Examples Are a Natural Consequence of Test Error in Noise
- Adversarial Robustness May Be at Odds With Simplicity
- Adversarial Music: Real World Audio Adversary Against Wake-word Detection System
- On the Sensitivity of Adversarial Robustness to Input Data Distributions