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 101–114 of 114 papers

TitleStatusHype
Playing to Learn Better: Repeated Games for Adversarial Learning with Multiple Classifiers—0
FastWordBug: A Fast Method To Generate Adversarial Text Against NLP Applications—0
Identifying Adversarial Sentences by Analyzing Text Complexity—0
Universal Adversarial Perturbation for Text Classification—0
AdvCodec: Towards A Unified Framework for Adversarial Text Generation—0
Evaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial ExamplesCode0
TextBugger: Generating Adversarial Text Against Real-world ApplicationsCode0
Discrete Adversarial Attacks and Submodular Optimization with Applications to Text ClassificationCode0
Adversarial Text Generation Without Reinforcement Learning—0
SALSA-TEXT : self attentive latent space based adversarial text generation—0
Adversarial Text Generation via Feature-Mover's DistanceCode0
Fooling OCR Systems with Adversarial Text Images—0
DANCin SEQ2SEQ: Fooling Text Classifiers with Adversarial Text Example GenerationCode0
Towards Crafting Text Adversarial Samples—0
Show:102550
← PrevPage 3 of 3Next →

No leaderboard results yet.