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 51–60 of 114 papers

TitleStatusHype
Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine TranslationCode0
VoteTRANS: Detecting Adversarial Text without Training by Voting on Hard Labels of TransformationsCode0
Generating Watermarked Adversarial Texts—0
CAT-Gen: Improving Robustness in NLP Models via Controlled Adversarial Text Generation—0
Goal-guided Generative Prompt Injection Attack on Large Language Models—0
Hierarchical Lexical Manifold Projection in Large Language Models: A Novel Mechanism for Multi-Scale Semantic Representation—0
How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacks—0
IAE: Irony-based Adversarial Examples for Sentiment Analysis Systems—0
Identifying Adversarial Attacks on Text Classifiers—0
Identifying Adversarial Sentences by Analyzing Text Complexity—0
Show:102550
← PrevPage 6 of 12Next →

No leaderboard results yet.