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 1–50 of 114 papers

TitleStatusHype
RETSim: Resilient and Efficient Text SimilarityCode4
Ignore Previous Prompt: Attack Techniques For Language ModelsCode2
Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial ExamplesCode2
BAE: BERT-based Adversarial Examples for Text ClassificationCode2
Dissecting Adversarial Robustness of Multimodal LM AgentsCode2
RETVec: Resilient and Efficient Text VectorizerCode2
TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLPCode2
Black-box Generation of Adversarial Text Sequences to Evade Deep Learning ClassifiersCode1
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and EntailmentCode1
White-box Multimodal Jailbreaks Against Large Vision-Language ModelsCode1
AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion modelsCode1
Adversarial Text Rewriting for Text-aware Recommender SystemsCode1
Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial TrajectoryCode1
"That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial AttacksCode1
SemAttack: Natural Textual Attacks via Different Semantic SpacesCode1
A Pilot Study of Query-Free Adversarial Attack against Stable DiffusionCode1
End-to-End Adversarial Text-to-SpeechCode1
MATE-KD: Masked Adversarial TExt, a Companion to Knowledge DistillationCode1
Persistent Anti-Muslim Bias in Large Language ModelsCode1
Few-Shot Adversarial Prompt Learning on Vision-Language ModelsCode1
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted AttackCode1
Semantic-Preserving Adversarial Text AttacksCode1
Generating Natural Language Attacks in a Hard Label Black Box SettingCode1
Generative Adversarial Text to Image SynthesisCode1
Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the WildCode1
Adversarial Decoding: Generating Readable Documents for Adversarial ObjectivesCode1
RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural PromptsCode1
Breaking BERT: Gradient Attack on Twitter Sentiment Analysis for Targeted MisclassificationCode0
TextBugger: Generating Adversarial Text Against Real-world ApplicationsCode0
BinarySelect to Improve Accessibility of Black-Box Attack ResearchCode0
BERT Lost Patience Won't Be Robust to Adversarial SlowdownCode0
Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text AttacksCode0
Frauds Bargain Attack: Generating Adversarial Text Samples via Word Manipulation ProcessCode0
StealthRank: LLM Ranking Manipulation via Stealthy Prompt OptimizationCode0
TAPE: Assessing Few-shot Russian Language UnderstandingCode0
TSCheater: Generating High-Quality Tibetan Adversarial Texts via Visual SimilarityCode0
Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal PerspectiveCode0
Arabic Synonym BERT-based Adversarial Examples for Text ClassificationCode0
Discrete Adversarial Attacks and Submodular Optimization with Applications to Text ClassificationCode0
Evaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial ExamplesCode0
SEPP: Similarity Estimation of Predicted Probabilities for Defending and Detecting Adversarial TextCode0
EMPRA: Embedding Perturbation Rank Attack against Neural Ranking ModelsCode0
Adversarial Text Generation via Feature-Mover's DistanceCode0
NMT-Obfuscator Attack: Ignore a sentence in translation with only one wordCode0
Less is More: Removing Text-regions Improves CLIP Training Efficiency and RobustnessCode0
DANCin SEQ2SEQ: Fooling Text Classifiers with Adversarial Text Example GenerationCode0
A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual ModelsCode0
Adversarial Robustness of Neural-Statistical Features in Detection of Generative TransformersCode0
R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion ModelCode0
SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text GenerationCode0
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.