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 6170 of 114 papers

TitleStatusHype
PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization0
Improved Training of Mixture-of-Experts Language GANs0
Improving Adversarial Text Generation by Modeling the Distant Future0
Improving Adversarial Text Generation with n-Gram Matching0
Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion0
Iterative Adversarial Attack on Image-guided Story Ending Generation0
AdvCodec: Towards A Unified Framework for Adversarial Text Generation0
A survey on text generation using generative adversarial networks0
Meta-CoTGAN: A Meta Cooperative Training Paradigm for Improving Adversarial Text Generation0
“That Is a Suspicious Reaction!”: Interpreting Logits Variation to Detect NLP Adversarial Attacks0
Show:102550
← PrevPage 7 of 12Next →

No leaderboard results yet.