Towards Crafting Text Adversarial Samples

2017/07/10 by Suranjana Samanta, Samanta, Suranjana, Sameep Mehta +1 · 6 citations
Computer Science · #Advanced Malware Detection Techniques #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Security and Verification in Computing

paper · pdf · doi:10.48550/arxiv.1707.02812

openalex publication_date 2017/07/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Intriguing properties of neural networks

Cited by

• Adversarial Attack and Defense of Structured Prediction Models
• Attack Graph Convolutional Networks by Adding Fake Nodes
• Adversarial Subword Regularization for Robust Neural Machine Translation
• MultiPhishGuard: An LLM-based Multi-Agent System for Phishing Email Detection
• To Transfer or Not to Transfer: Misclassification Attacks Against\n Transfer Learned Text Classifiers
• Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification

Related

• DANCin SEQ2SEQ: Fooling Text Classifiers with Adversarial Text Example Generation
• Detection of Word Adversarial Examples in Text Classification: Benchmark and Baseline via Robust Density Estimation
• Generating Natural Language Adversarial Examples on a Large Scale with Generative Models
• Attacking Misinformation Detection Using Adversarial Examples Generated by Language Models
• R&R: Metric-guided Adversarial Sentence Generation