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 71–80 of 114 papers

TitleStatusHype
TAPE: Assessing Few-shot Russian Language UnderstandingCode0
PARSE: An Efficient Search Method for Black-box Adversarial Text Attacks—0
Adversarial Text Normalization—0
Detecting Word-Level Adversarial Text Attacks via SHapley Additive exPlanations—0
“That Is a Suspicious Reaction!”: Interpreting Logits Variation to Detect NLP Adversarial Attacks—0
Adversarial Robustness of Neural-Statistical Features in Detection of Generative TransformersCode0
Data-Driven Mitigation of Adversarial Text Perturbation—0
Identifying Adversarial Attacks on Text Classifiers—0
SemAttack: Natural Textual Attacks via Different Semantic Spaces—0
Repairing Adversarial Texts through Perturbation—0
Show:102550
← PrevPage 8 of 12Next →

No leaderboard results yet.