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

Showing 110 of 114 papers

TitleStatusHype
RETSim: Resilient and Efficient Text SimilarityCode4
Ignore Previous Prompt: Attack Techniques For Language ModelsCode2
BAE: BERT-based Adversarial Examples for Text ClassificationCode2
Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial ExamplesCode2
RETVec: Resilient and Efficient Text VectorizerCode2
Dissecting Adversarial Robustness of Multimodal LM AgentsCode2
TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLPCode2
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted AttackCode1
Adversarial Text Rewriting for Text-aware Recommender SystemsCode1
Black-box Generation of Adversarial Text Sequences to Evade Deep Learning ClassifiersCode1
Show:102550
← PrevPage 1 of 12Next →

No leaderboard results yet.