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 101–114 of 114 papers

TitleStatusHype
DISCO : efficient unsupervised decoding for discrete natural language problems via convex relaxation—0
Enhancing Adversarial Text Attacks on BERT Models with Projected Gradient Descent—0
Don't Search for a Search Method -- Simple Heuristics Suffice for Adversarial Text Attacks—0
Don’t Search for a Search Method — Simple Heuristics Suffice for Adversarial Text Attacks—0
TextDefense: Adversarial Text Detection based on Word Importance Entropy—0
Data-Driven Mitigation of Adversarial Text Perturbation—0
FastWordBug: A Fast Method To Generate Adversarial Text Against NLP Applications—0
Continuous Adversarial Text Representation Learning for Affective Recognition—0
Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization—0
Fooling OCR Systems with Adversarial Text Images—0
"That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial Attacks—0
From Unsupervised Machine Translation To Adversarial Text Generation—0
Generating Natural Language Adversarial Examples on a Large Scale with Generative Models—0
Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?—0
Show:102550
← PrevPage 3 of 3Next →

No leaderboard results yet.