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
SEPP: Similarity Estimation of Predicted Probabilities for Defending and Detecting Adversarial TextCode0
EMPRA: Embedding Perturbation Rank Attack against Neural Ranking ModelsCode0
Adversarial Text Generation via Feature-Mover's DistanceCode0
NMT-Obfuscator Attack: Ignore a sentence in translation with only one wordCode0
Less is More: Removing Text-regions Improves CLIP Training Efficiency and RobustnessCode0
DANCin SEQ2SEQ: Fooling Text Classifiers with Adversarial Text Example GenerationCode0
A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual ModelsCode0
Adversarial Robustness of Neural-Statistical Features in Detection of Generative TransformersCode0
R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion ModelCode0
SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text GenerationCode0
Show:102550
← PrevPage 5 of 12Next →

No leaderboard results yet.