Towards Crafting Text Adversarial Samples

Abstract

Adversarial samples are strategically modified samples, which are crafted with the purpose of fooling a classifier at hand. An attacker introduces specially crafted adversarial samples to a deployed classifier, which are being mis-classified by the classifier. However, the samples are perceived to be drawn from entirely different classes and thus it becomes hard to detect the adversarial samples. Most of the prior works have been focused on synthesizing adversarial samples in the image domain. In this paper, we propose a new method of crafting adversarial text samples by modification of the original samples. Modifications of the original text samples are done by deleting or replacing the important or salient words in the text or by introducing new words in the text sample. Our algorithm works best for the datasets which have sub-categories within each of the classes of examples. While crafting adversarial samples, one of the key constraint is to generate meaningful sentences which can at pass off as legitimate from language (English) viewpoint. Experimental results on IMDB movie review dataset for sentiment analysis and Twitter dataset for gender detection show the efficiency of our proposed method.

11 pages, 5 figues

References in corpus (3)

• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• Adversarial examples for generative models

Cited by in corpus (53)

• Synthetic and Natural Noise Both Break Neural Machine Translation
• TextBugger: Generating Adversarial Text Against Real-world Applications
• Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey
• A Review of Adversarial Attack and Defense for Classification Methods
• Reevaluating Adversarial Examples in Natural Language
• Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
• Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers
• Attack Graph Convolutional Networks by Adding Fake Nodes
• Dynamic Time Warping based Adversarial Framework for Time-Series Domain
• Adversarial Robustness of Deep Code Comment Generation
• Interpretable Adversarial Perturbation in Input Embedding Space for Text
• Fooling OCR Systems with Adversarial Text Images
• Natural Language Adversarial Defense through Synonym Encoding
• Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble
• Greedy Attack and Gumbel Attack: Generating Adversarial Examples for Discrete Data
• Towards a Robust Deep Neural Network in Texts: A Survey
• Self-Explaining Structures Improve NLP Models
• Contextualized Perturbation for Textual Adversarial Attack
• Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification
• Towards Robust Toxic Content Classification
• On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models
• Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Features
• Adversarial Attacks and Defense on Texts: A Survey
• Generating Natural Language Adversarial Examples on a Large Scale with Generative Models
• Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis
• Security and Privacy for Artificial Intelligence: Opportunities and Challenges
• Silent Guardian: Protecting Text from Malicious Exploitation by Large Language Models
• To Transfer or Not to Transfer: Misclassification Attacks Against Transfer Learned Text Classifiers
• FastWordBug: A Fast Method To Generate Adversarial Text Against NLP Applications
• TREATED:Towards Universal Defense against Textual Adversarial Attacks
• Negative Training for Neural Dialogue Response Generation
• Adversarial Attack and Defense of Structured Prediction Models
• Differentiable Language Model Adversarial Attacks on Categorical Sequence Classifiers
• T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack
• Analysis Methods in Neural Language Processing: A Survey
• Adversarial Subword Regularization for Robust Neural Machine Translation
• Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation
• Gradient-based Adversarial Attacks against Text Transformers
• Improving Robustness of Malware Classifiers using Adversarial Strings Generated from Perturbed Latent Representations
• Robustness to Modification with Shared Words in Paraphrase Identification
• Adversarial Dropout for Recurrent Neural Networks
• Challenge AI Mind: A Crowd System for Proactive AI Testing
• Learning Neural Models for Natural Language Processing in the Face of Distributional Shift
• Extending Adversarial Attacks to Produce Adversarial Class Probability Distributions
• Gödel's Sentence Is An Adversarial Example But Unsolvable
• Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing
• What's in a Name? Are BERT Named Entity Representations just as Good for any other Name?
• On the Transferability of Adversarial Attacksagainst Neural Text Classifier
• Evaluating Document Coherence Modelling
• Natural Adversarial Sentence Generation with Gradient-based Perturbation
• Robustness Tests of NLP Machine Learning Models: Search and Semantically Replace
• Universal Physical Camouflage Attacks on Object Detectors
• Adversarially Robust and Explainable Model Compression with On-Device Personalization for Text Classification