DeepAI AI Chat
Log In Sign Up

Generating Natural Adversarial Examples

by   Zhengli Zhao, et al.
University of California, Irvine

Due to their complex nature, it is hard to characterize the ways in which machine learning models can misbehave or be exploited when deployed. Recent work on adversarial examples, i.e. inputs with minor perturbations that result in substantially different model predictions, is helpful in evaluating the robustness of these models by exposing the adversarial scenarios where they fail. However, these malicious perturbations are often unnatural, not semantically meaningful, and not applicable to complicated domains such as language. In this paper, we propose a framework to generate natural and legible adversarial examples by searching in semantic space of dense and continuous data representation, utilizing the recent advances in generative adversarial networks. We present generated adversaries to demonstrate the potential of the proposed approach for black-box classifiers in a wide range of applications such as image classification, textual entailment, and machine translation. We include experiments to show that the generated adversaries are natural, legible to humans, and useful in evaluating and analyzing black-box classifiers.


page 2

page 4

page 7


Structure-Preserving Transformation: Generating Diverse and Transferable Adversarial Examples

Adversarial examples are perturbed inputs designed to fool machine learn...

ManiGen: A Manifold Aided Black-box Generator of Adversarial Examples

Machine learning models, especially neural network (NN) classifiers, hav...

On Adversarial Examples for Character-Level Neural Machine Translation

Evaluating on adversarial examples has become a standard procedure to me...

Plausible Counterfactuals: Auditing Deep Learning Classifiers with Realistic Adversarial Examples

The last decade has witnessed the proliferation of Deep Learning models ...

Adversarial Examples for Semantic Segmentation and Object Detection

It has been well demonstrated that adversarial examples, i.e., natural i...

DANCin SEQ2SEQ: Fooling Text Classifiers with Adversarial Text Example Generation

Machine learning models are powerful but fallible. Generating adversaria...

Additive Tree Ensembles: Reasoning About Potential Instances

Imagine being able to ask questions to a black box model such as "Which ...