Adversarial Machine Learning in Text Analysis and Generation

Abstract

The research field of adversarial machine learning witnessed a significant interest in the last few years. A machine learner or model is secure if it can deliver main objectives with acceptable accuracy, efficiency, etc. while at the same time, it can resist different types and/or attempts of adversarial attacks. This paper focuses on studying aspects and research trends in adversarial machine learning specifically in text analysis and generation. The paper summarizes main research trends in the field such as GAN algorithms, models, types of attacks, and defense against those attacks.

References in corpus (49)

• Auto-Encoding Variational Bayes
• Sequence to Sequence Learning with Neural Networks
• Generative Adversarial Networks: An Overview
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Categorical Reparameterization with Gumbel-Softmax
• Microsoft COCO Captions: Data Collection and Evaluation Server
• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
• A Neural Conversational Model
• Exploring the Limits of Language Modeling
• Certified Adversarial Robustness via Randomized Smoothing
• Understanding Neural Networks through Representation Erasure
• Adversarial Attacks and Defences: A Survey
• Deep Text Classification Can be Fooled
• MaskGAN: Better Text Generation via Filling in the______
• Professor Forcing: A New Algorithm for Training Recurrent Networks
• Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
• A Survey of Knowledge-Enhanced Text Generation
• Exploration by Random Network Distillation
• An Actor-Critic Algorithm for Sequence Prediction
• GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
• Stochastic Activation Pruning for Robust Adversarial Defense
• On Adversarial Examples for Character-Level Neural Machine Translation
• Adversarial Ranking for Language Generation
• Deceiving Google's Perspective API Built for Detecting Toxic Comments
• Generative Adversarial Networks for Spatio-temporal Data: A Survey
• The Robust Manifold Defense: Adversarial Training using Generative Models
• Adversarial Generation of Natural Language
• Probabilistic Forecasting of Sensory Data with Generative Adversarial Networks - ForGAN
• Adversarial Text Generation via Feature-Mover's Distance
• ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation
• Adversarial Texts with Gradient Methods
• Neural Text Generation: Past, Present and Beyond
• Logit Pairing Methods Can Fool Gradient-Based Attacks
• Generating Text with Deep Reinforcement Learning
• LSTM vs. GRU vs. Bidirectional RNN for script generation
• Eval all, trust a few, do wrong to none: Comparing sentence generation models
• Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble
• D-GAN: Deep Generative Adversarial Nets for Spatio-Temporal Prediction
• Evaluating Text GANs as Language Models
• Improving Sequence-to-Sequence Learning via Optimal Transport
• DANCin SEQ2SEQ: Fooling Text Classifiers with Adversarial Text Example Generation
• Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation
• Adversarial Generalized Method of Moments
• Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification
• Judge the Judges: A Large-Scale Evaluation Study of Neural Language Models for Online Review Generation
• Text Generation with Exemplar-based Adaptive Decoding
• GraphPB: Graphical Representations of Prosody Boundary in Speech Synthesis
• Understanding and Diagnosing Vulnerability under Adversarial Attacks
• Random Network Distillation as a Diversity Metric for Both Image and Text Generation