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 91100 of 114 papers

TitleStatusHype
SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text GenerationCode0
StealthRank: LLM Ranking Manipulation via Stealthy Prompt OptimizationCode0
Less is More: Removing Text-regions Improves CLIP Training Efficiency and RobustnessCode0
Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text AttacksCode0
NMT-Obfuscator Attack: Ignore a sentence in translation with only one wordCode0
VoteTRANS: Detecting Adversarial Text without Training by Voting on Hard Labels of TransformationsCode0
Evaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial ExamplesCode0
Frauds Bargain Attack: Generating Adversarial Text Samples via Word Manipulation ProcessCode0
Arabic Synonym BERT-based Adversarial Examples for Text ClassificationCode0
TAPE: Assessing Few-shot Russian Language UnderstandingCode0
Show:102550
← PrevPage 10 of 12Next →

No leaderboard results yet.