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 21–30 of 114 papers

TitleStatusHype
Generating Natural Language Attacks in a Hard Label Black Box SettingCode1
Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the WildCode1
End-to-End Adversarial Text-to-SpeechCode1
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted AttackCode1
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and EntailmentCode1
Black-box Generation of Adversarial Text Sequences to Evade Deep Learning ClassifiersCode1
Generative Adversarial Text to Image SynthesisCode1
Adversarial Text Generation with Dynamic Contextual Perturbation—0
StealthRank: LLM Ranking Manipulation via Stealthy Prompt OptimizationCode0
Breaking BERT: Gradient Attack on Twitter Sentiment Analysis for Targeted MisclassificationCode0
Show:102550
← PrevPage 3 of 12Next →

No leaderboard results yet.