Textual Adversarial Attack

Textual adversarial attacks involve subtly altering text inputs to mislead natural language processing (NLP) models, primarily focusing on evaluating and improving model robustness. Current research emphasizes developing more effective attack methods, often leveraging gradient-based optimization and incorporating semantic similarity constraints within models like BERT, as well as creating stronger defenses through techniques such as adversarial training and randomized smoothing. This field is crucial for ensuring the reliability and security of NLP systems across various applications, from text classification to machine translation, by identifying and mitigating vulnerabilities to malicious manipulation.

Papers

October 11, 2024

NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models
Zheng Yi Ho, Siyuan Liang, Sen Zhang, Yibing Zhan, Dacheng Tao
Language Model Attention Head Textual Adversarial Attack De Novo Path Norm

August 19, 2024

Enhance Modality Robustness in Text-Centric Multimodal Alignment with Adversarial Prompting
Yun-Da Tsai, Ting-Yu Yen, Keng-Te Liao, Shou-De Lin
Multimodal Model Multimodal Representation Multimodal Alignment Textual Adversarial Attack Adversarial Prompting Modality Robustness

July 29, 2024

Enhancing Adversarial Text Attacks on BERT Models with Projected Gradient Descent
Hetvi Waghela, Jaydip Sen, Sneha Rakshit
Adversarial Attack Adversarial Example Textual Adversarial Attack Projected Gradient Descent

June 18, 2024

Saliency Attention and Semantic Similarity-Driven Adversarial Perturbation
Hetvi Waghela, Jaydip Sen, Sneha Rakshit
Adversarial Example Textual Adversarial Attack Traditional Adversarial Word Saliency

May 25, 2024

R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model
Changhoon Kim, Kyle Min, Yezhou Yang
Text to Image Diffusion Model Text to Image Adversarial Framework Textual Adversarial Attack Adversarial Challenge

April 8, 2024

Semantic Stealth: Adversarial Text Attacks on NLP Using Several Methods
Roopkatha Dey, Aivy Debnath, Sayak Kumar Dutta, Kaustav Ghosh, Arijit Mitra, Arghya Roy Chowdhury, Jaydip Sen
Adversarial Attack Adversarial Example Practical Method NLP Field BERT Based Textual Adversarial Attack Digital STEALTH Metric Victim Model

February 29, 2024

MPAT: Building Robust Deep Neural Networks against Textual Adversarial Attacks
Fangyuan Zhang, Huichi Zhou, Shuangjiao Li, Hongtao Wang
Adversarial Attack Adversarial Example Adversarial Training Robust Deep Textual Adversarial Attack

February 5, 2024

Arabic Synonym BERT-based Adversarial Examples for Text Classification
Norah Alshahrani, Saied Alshahrani, Esma Wali, Jeanna Matthews
Adversarial Attack Adversarial Example Text Classification Textual Adversarial Attack Textual Adversarial Example Arabic BERt

January 23, 2024

Fast Adversarial Training against Textual Adversarial Attacks
Yichen Yang, Xin Liu, Kun He
Adversarial Training Adversarial Robustness Adversarial Perturbation Textual Adversarial Attack Fast Adversarial Training

January 7, 2024

ROIC-DM: Robust Text Inference and Classification via Diffusion Model
Shilong Yuan, Wei Yuan, Hongzhi Yin, Tieke He
Language Model Diffusion Model Classification Code Natural Language Inference Textual Adversarial Attack

November 29, 2023

Improving the Robustness of Transformer-based Large Language Models with Dynamic Attention
Lujia Shen, Yuwen Pu, Shouling Ji, Changjiang Li, Xuhong Zhang, Chunpeng Ge, Ting Wang
Adversarial Attack Native Robustness Adversarial Training Attention Mechanism Transformer Based Large Language Model Textual Adversarial Attack Dynamic Attention

October 21, 2023

Toward Stronger Textual Attack Detectors
Pierre Colombo, Marine Picot, Nathan Noiry, Guillaume Staerman, Pablo Piantanida
NLP Community Textual Adversarial Attack Textual Attack

July 31, 2023

Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks
Xinyu Zhang, Hanbin Hong, Yuan Hong, Peng Huang, Binghui Wang, Zhongjie Ba, Kui Ren
Textual Adversarial Attack Certified Robustness Synonym Substitution Attack Word Level Adversarial Insertion Based

July 24, 2023

Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation
Neel Bhandari, Pin-Yu Chen
Adversarial Attack Adversarial Example View Translation Textual Adversarial Attack Cross Lingual Backdoor Attack

July 4, 2023

SCAT: Robust Self-supervised Contrastive Learning via Adversarial Training for Text Classification
Junjie Wu, Dit-Yan Yeung
Contrastive Learning Adversarial Example Adversarial Training Text Classification Robust Version Textual Adversarial Attack

June 27, 2023

DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization
Songyang Gao, Shihan Dou, Yan Liu, Xiao Wang, Qi Zhang, Zhongyu Wei, Jin Ma, Ying Shan
Language Model Adversarial Training Distribution Shift Adversarial Loss Textual Adversarial Attack

June 7, 2023

PromptBench: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts
Kaijie Zhu, Jindong Wang, Jiaheng Zhou, Zichen Wang, Hao Chen, Yidong Wang, Linyi Yang, Wei Ye, Yue Zhang, Neil Zhenqiang Gong, Xing Xie
Native Robustness Adversarial Prompt Textual Adversarial Attack Robustness Analysis

February 18, 2023

RETVec: Resilient and Efficient Text Vectorizer
Elie Bursztein, Marina Zhang, Owen Vallis, Xinyu Jia, Alexey Kurakin
Multilingual Model Word Embeddings Tiny Refinement Elicit Resilience Textual Adversarial Attack

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 10, 2023

Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks
Piotr Gaiński, Klaudia Bałazy
Adversarial Example Transformer Based Language Model Text Representation Cross Over Step Adversarial Loss Gradient Based Attack Textual Adversarial Attack Step Count

Textual Adversarial Attack

Papers

NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models

Enhance Modality Robustness in Text-Centric Multimodal Alignment with Adversarial Prompting

Enhancing Adversarial Text Attacks on BERT Models with Projected Gradient Descent

Saliency Attention and Semantic Similarity-Driven Adversarial Perturbation

R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model

Semantic Stealth: Adversarial Text Attacks on NLP Using Several Methods

MPAT: Building Robust Deep Neural Networks against Textual Adversarial Attacks

Arabic Synonym BERT-based Adversarial Examples for Text Classification

Fast Adversarial Training against Textual Adversarial Attacks

ROIC-DM: Robust Text Inference and Classification via Diffusion Model

Improving the Robustness of Transformer-based Large Language Models with Dynamic Attention

Toward Stronger Textual Attack Detectors

Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks

Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation

SCAT: Robust Self-supervised Contrastive Learning via Adversarial Training for Text Classification

DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization

PromptBench: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts

RETVec: Resilient and Efficient Text Vectorizer

TextDefense: Adversarial Text Detection based on Word Importance Entropy

Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks