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 41–50 of 114 papers

TitleStatusHype
NMT-Obfuscator Attack: Ignore a sentence in translation with only one wordCode0
IAE: Irony-based Adversarial Examples for Sentiment Analysis Systems—0
Target-driven Attack for Large Language Models—0
Graded Suspiciousness of Adversarial Texts to Human—0
Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine TranslationCode0
OpenFact at CheckThat! 2024: Combining Multiple Attack Methods for Effective Adversarial Text Generation—0
Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion—0
Enhancing Adversarial Text Attacks on BERT Models with Projected Gradient Descent—0
Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?—0
Phantom: General Trigger Attacks on Retrieval Augmented Language Generation—0
Show:102550
← PrevPage 5 of 12Next →

No leaderboard results yet.