DANCin SEQ2SEQ: Fooling Text Classifiers with Adversarial Text Example Generation

Abstract

Machine learning models are powerful but fallible. Generating adversarial examples - inputs deliberately crafted to cause model misclassification or other errors - can yield important insight into model assumptions and vulnerabilities. Despite significant recent work on adversarial example generation targeting image classifiers, relatively little work exists exploring adversarial example generation for text classifiers; additionally, many existing adversarial example generation algorithms require full access to target model parameters, rendering them impractical for many real-world attacks. In this work, we introduce DANCin SEQ2SEQ, a GAN-inspired algorithm for adversarial text example generation targeting largely black-box text classifiers. We recast adversarial text example generation as a reinforcement learning problem, and demonstrate that our algorithm offers preliminary but promising steps towards generating semantically meaningful adversarial text examples in a real-world attack scenario.

References in corpus (4)

• Explaining and Harnessing Adversarial Examples
• Synthesizing Robust Adversarial Examples
• Adversarial Examples for Evaluating Reading Comprehension Systems
• Adversarial Learning for Neural Dialogue Generation

Cited by in corpus (7)

• Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey
• Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble
• Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classification
• Rewriting Meaningful Sentences via Conditional BERT Sampling and an application on fooling text classifiers
• R&R: Metric-guided Adversarial Sentence Generation
• On the Transferability of Adversarial Attacksagainst Neural Text Classifier
• Adversarial Machine Learning in Text Analysis and Generation