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 91–100 of 114 papers

TitleStatusHype
Detecting Adversarial Text Attacks via SHapley Additive exPlanations—0
"TL;DR:" Out-of-Context Adversarial Text Summarization and Hashtag Recommendation—0
Adversarial Text-to-Image Synthesis: A Review—0
From Unsupervised Machine Translation To Adversarial Text Generation—0
Adversarial Text Generation via Sequence Contrast Discrimination—0
CAT-Gen: Improving Robustness in NLP Models via Controlled Adversarial Text Generation—0
What Machines See Is Not What They Get: Fooling Scene Text Recognition Models With Adversarial Text Images—0
Improving Adversarial Text Generation by Modeling the Distant Future—0
Meta-CoTGAN: A Meta Cooperative Training Paradigm for Improving Adversarial Text Generation—0
Generating Natural Language Adversarial Examples on a Large Scale with Generative Models—0
Show:102550
← PrevPage 10 of 12Next →

No leaderboard results yet.