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

Showing 4150 of 114 papers

TitleStatusHype
Towards a Robust Detection of Language Model Generated Text: Is ChatGPT that Easy to Detect?0
VoteTRANS: Detecting Adversarial Text without Training by Voting on Hard Labels of TransformationsCode0
How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacks0
Iterative Adversarial Attack on Image-guided Story Ending Generation0
Less is More: Removing Text-regions Improves CLIP Training Efficiency and RobustnessCode0
Towards Imperceptible Document Manipulations against Neural Ranking Models0
A Pilot Study of Query-Free Adversarial Attack against Stable DiffusionCode1
Frauds Bargain Attack: Generating Adversarial Text Samples via Word Manipulation ProcessCode0
Improved Training of Mixture-of-Experts Language GANs0
RETVec: Resilient and Efficient Text VectorizerCode2
Show:102550
← PrevPage 5 of 12Next →

No leaderboard results yet.