Textual Attack

Textual attacks involve crafting subtly altered text inputs to deceive natural language processing (NLP) models, primarily those based on transformer architectures like BERT. Current research focuses on developing more effective attack methods, such as those leveraging beam search and diverse semantic spaces to generate high-quality adversarial examples, and simultaneously improving defenses, including techniques that analyze attention mechanisms and learn from the training data distribution to identify and mitigate attacks. This field is crucial for ensuring the robustness and trustworthiness of NLP systems across various applications, from sentiment analysis to cybersecurity, where vulnerabilities to such attacks can have significant consequences.

Papers

April 17, 2024

GenFighter: A Generative and Evolutive Textual Attack Removal
Md Athikul Islam, Edoardo Serra, Sushil Jajodia
Adversarial Attack Adversarial Robustness Generative Question State of the Art Defense Defense Method Textual Attack

February 26, 2024

Unveiling Vulnerability of Self-Attention
Khai Jiet Liong, Hongqiu Wu, Hai Zhao
Language Model Adversarial Training Self Attention Level Perturbation Unveiling Vulnerability Textual Attack

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

March 9, 2023

BeamAttack: Generating High-quality Textual Adversarial Examples through Beam Search and Mixed Semantic Spaces
Hai Zhu, Qingyang Zhao, Yuren Wu
Adversarial Example Adversarial Training Beam Search Semantic Space Textual Adversarial Example Word Level Attack Textual Attack

November 1, 2022

Looking Beyond IoCs: Automatically Extracting Attack Patterns from External CTI
Md Tanvirul Alam, Dipkamal Bhusal, Youngja Park, Nidhi Rastogi
Threat Intelligence Attack Pattern Textual Attack Cyberthreat Intelligence

May 3, 2022

SemAttack: Natural Textual Attacks via Different Semantic Spaces
Boxin Wang, Chejian Xu, Xiangyu Liu, Yu Cheng, Bo Li
Adversarial Text Semantic Space Textual Adversarial Attack Textual Attack