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 81–90 of 114 papers

TitleStatusHype
"That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial Attacks—0
“That Is a Suspicious Reaction!”: Interpreting Logits Variation to Detect NLP Adversarial Attacks—0
"TL;DR:" Out-of-Context Adversarial Text Summarization and Hashtag Recommendation—0
Towards a Robust Detection of Language Model Generated Text: Is ChatGPT that Easy to Detect?—0
Towards Crafting Text Adversarial Samples—0
Towards Imperceptible Document Manipulations against Neural Ranking Models—0
Universal Adversarial Perturbation for Text Classification—0
What Machines See Is Not What They Get: Fooling Scene Text Recognition Models With Adversarial Text Images—0
What Models Know About Their Attackers: Deriving Attacker Information From Latent Representations—0
SEPP: Similarity Estimation of Predicted Probabilities for Defending and Detecting Adversarial TextCode0
Show:102550
← PrevPage 9 of 12Next →

No leaderboard results yet.