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 31–40 of 114 papers

TitleStatusHype
Semantic Stealth: Adversarial Text Attacks on NLP Using Several Methods—0
Goal-guided Generative Prompt Injection Attack on Large Language Models—0
Few-Shot Adversarial Prompt Learning on Vision-Language ModelsCode1
Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial TrajectoryCode1
A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual ModelsCode0
Adversarial Text Purification: A Large Language Model Approach for Defense—0
Arabic Synonym BERT-based Adversarial Examples for Text ClassificationCode0
Adversarial Text to Continuous Image Generation—0
RETSim: Resilient and Efficient Text SimilarityCode4
BERT Lost Patience Won't Be Robust to Adversarial SlowdownCode0
Show:102550
← PrevPage 4 of 12Next →

No leaderboard results yet.