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 11–20 of 114 papers

TitleStatusHype
Black-box Generation of Adversarial Text Sequences to Evade Deep Learning ClassifiersCode1
Adversarial Text Rewriting for Text-aware Recommender SystemsCode1
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and EntailmentCode1
Generating Natural Language Attacks in a Hard Label Black Box SettingCode1
End-to-End Adversarial Text-to-SpeechCode1
Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial TrajectoryCode1
AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion modelsCode1
Few-Shot Adversarial Prompt Learning on Vision-Language ModelsCode1
A Pilot Study of Query-Free Adversarial Attack against Stable DiffusionCode1
Generative Adversarial Text to Image SynthesisCode1
Show:102550
← PrevPage 2 of 12Next →

No leaderboard results yet.