SOTAVerified

Adversarial Text

Adversarial Text refers to a specialised text sequence that is designed specifically to influence the prediction of a language model. Generally, Adversarial Text attack are carried out on Large Language Models (LLMs). Research on understanding different adversarial approaches can help us build effective defense mechanisms to detect malicious text input and build robust language models.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 71–80 of 114 papers

TitleStatusHype
OpenFact at CheckThat! 2024: Combining Multiple Attack Methods for Effective Adversarial Text Generation—0
PARSE: An Efficient Search Method for Black-box Adversarial Text Attacks—0
A Grey-box Text Attack Framework using Explainable AI—0
Phantom: General Trigger Attacks on Retrieval Augmented Language Generation—0
Playing to Learn Better: Repeated Games for Adversarial Learning with Multiple Classifiers—0
"TL;DR:" Out-of-Context Adversarial Text Summarization and Hashtag Recommendation—0
Reinforce Attack: Adversarial Attack against BERT with Reinforcement Learning—0
Repairing Adversarial Texts through Perturbation—0
Adversarial Training: A simple and efficient technique to Improving NLP Robustness—0
Adversarial Text-to-Image Synthesis: A Review—0
Show:102550
← PrevPage 8 of 12Next →

No leaderboard results yet.