Adversarial Text

Adversarial text research focuses on creating and defending against text inputs designed to deceive natural language processing (NLP) models, often by subtly altering wording while maintaining semantic similarity to a human reader. Current research emphasizes developing more effective attack methods, particularly those leveraging multi-agent systems, reinforcement learning, and diffusion models, as well as improving defenses through techniques like adversarial training and noise augmentation. This field is crucial for enhancing the robustness and trustworthiness of NLP systems across diverse applications, from automated essay scoring to autonomous vehicle navigation and large language model safety.

Papers

May 24, 2023

How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacks
Salijona Dyrmishi, Salah Ghamizi, Maxime Cordy
Adversarial Attack Adversarial Example Adversarial Perturbation Adversarial Text Concurrent Validity Visual Naturalness Text Attack Reality Check Word Level Adversarial

May 16, 2023

Iterative Adversarial Attack on Image-guided Story Ending Generation
Youze Wang, Wenbo Hu, Richang Hong
Adversarial Text Modal Attack Multimodal Attack Multimodal Text Generation

April 21, 2023

RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Models
Seulki Park, Daeho Um, Hajung Yoon, Sanghyuk Chun, Sangdoo Yun
Adversarial Text Image Text Matching Adversarial Data Robustness Benchmark V Coco Sg

April 8, 2023

Robust Deep Learning Models Against Semantic-Preserving Adversarial Attack
Dashan Gao, Yunce Zhao, Yinghua Yao, Zeqi Zhang, Bifei Mao, Xin Yao
Adversarial Attack Adversarial Training Adversarial Perturbation Adversarial Text Robust Training Robust Deep

March 31, 2023

Comparing Adversarial and Supervised Learning for Organs at Risk Segmentation in CT images
Leonardo Crespi, Mattia Portanti, Daniele Loiacono
Generative Adversarial Network Supervised Learning CT Image Adversarial Text Human Organ GAN Generated Image Risk Segmentation Organ at Risk

March 24, 2023

Generalist: Decoupling Natural and Robust Generalization
Hongjun Wang, Yisen Wang
Adversarial Example Adversarial Training Adversarial Text Robust Generalization Generalist Learner

March 2, 2023

February 22, 2023

On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective
Jindong Wang, Xixu Hu, Wenxin Hou, Hao Chen, Runkai Zheng, Yidong Wang, Linyi Yang, Haojun Huang, Wei Ye, Xiubo Geng, Binxin Jiao, Yue Zhang, Xing Xie
Native Robustness Adversarial Robustness ChatGPT Generated Conversation Adversarial Text Understanding Out of Distribution Spoken Dialogue

February 12, 2023

TextDefense: Adversarial Text Detection based on Word Importance Entropy
Lujia Shen, Xuhong Zhang, Shouling Ji, Yuwen Pu, Chunpeng Ge, Xing Yang, Yanghe Feng
Adversarial Attack Adversarial Example Adversarial Text Textual Adversarial Attack Text Attack Lexicon Entropy

February 5, 2023

Online Nonstochastic Control with Adversarial and Static Constraints
Xin Liu, Zixian Yang, Lei Ying
Adversarial Text Online Convex Optimization Nonstochastic Control

February 3, 2023

TextShield: Beyond Successfully Detecting Adversarial Sentences in Text Classification
Lingfeng Shen, Ze Zhang, Haiyun Jiang, Ying Chen
Adversarial Attack Text Classification Adversarial Text Text Attack

February 2, 2023

TransFool: An Adversarial Attack against Neural Machine Translation Models
Sahar Sadrizadeh, Ljiljana Dolamic, Pascal Frossard
Adversarial Attack Adversarial Example Neural Machine Translation Adversarial Text Neural Machine Translation Model

November 13, 2022

Adversarial and Random Transformations for Robust Domain Adaptation and Generalization
Liang Xiao, Jiaolong Xu, Dawei Zhao, Erke Shang, Qi Zhu, Bin Dai
Data Augmentation Strong Generalization Adversarial Example Adversarial Text Adversarial Augmentation Random Transformation Adversarial Data Augmentation Robust Domain Adaptation Random Data Augmentation

November 12, 2022

Generating Textual Adversaries with Minimal Perturbation
Xingyi Zhao, Lu Zhang, Depeng Xu, Shuhan Yuan
Adversarial Text Small Perturbation Attack Algorithm Word Level Adversarial

November 5, 2022

Textual Manifold-based Defense Against Natural Language Adversarial Examples
Dang Minh Nguyen, Luu Anh Tuan
Adversarial Attack Adversarial Example Adversarial Text Adversarial Image Textual Adversarial Example Manifold Attack

November 1, 2022

Comparision Of Adversarial And Non-Adversarial LSTM Music Generative Models
Moseli Mots'oehli, Anna Sergeevna Bosman, Johan Pieter De Villiers
Generative Adversarial Network Recurrent Neural Network Music Generation Adversarial Text Systematic Comparison Music Composition Generative Music Model

October 28, 2022

RoChBert: Towards Robust BERT Fine-tuning for Chinese
Zihan Zhang, Jinfeng Li, Ning Shi, Bo Yuan, Xiangyu Liu, Rong Zhang, Hui Xue, Donghong Sun, Chao Zhang
Language Model Pre Trained Language Model Chinese Character Adversarial Text Adversarial Graph Efficient BERT

October 22, 2022

There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning
Xueliang Zhao, Tingchen Fu, Chongyang Tao, Rui Yan
Adversarial Text Top Two Answer Knowledge Selection Multiple Knowledge Source Knowledge Grounded Dialogue Generation Multi Reference Set to Set

October 17, 2022

Adversarial and Safely Scaled Question Generation
Sreehari Sankar, Zhihang Dong
Large Language Model Question Generation Adversarial Text