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
R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion ModelCode0
TSCheater: Generating High-Quality Tibetan Adversarial Texts via Visual SimilarityCode0
Adversarial Text Generation via Feature-Mover's DistanceCode0
EMPRA: Embedding Perturbation Rank Attack against Neural Ranking ModelsCode0
Discrete Adversarial Attacks and Submodular Optimization with Applications to Text ClassificationCode0
Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal PerspectiveCode0
DANCin SEQ2SEQ: Fooling Text Classifiers with Adversarial Text Example GenerationCode0
TextBugger: Generating Adversarial Text Against Real-world ApplicationsCode0
A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual ModelsCode0
Breaking BERT: Gradient Attack on Twitter Sentiment Analysis for Targeted MisclassificationCode0
BinarySelect to Improve Accessibility of Black-Box Attack ResearchCode0
Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine TranslationCode0
Adversarial Robustness of Neural-Statistical Features in Detection of Generative TransformersCode0
BERT Lost Patience Won't Be Robust to Adversarial SlowdownCode0
Show:102550
← PrevPage 5 of 5Next →

No leaderboard results yet.