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
Dissecting Adversarial Robustness of Multimodal LM AgentsCode2
Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial ExamplesCode2
RETVec: Resilient and Efficient Text VectorizerCode2
TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLPCode2
BAE: BERT-based Adversarial Examples for Text ClassificationCode2
MATE-KD: Masked Adversarial TExt, a Companion to Knowledge DistillationCode1
SemAttack: Natural Textual Attacks via Different Semantic SpacesCode1
Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial TrajectoryCode1
Semantic-Preserving Adversarial Text AttacksCode1
Adversarial Text Rewriting for Text-aware Recommender SystemsCode1
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
End-to-End Adversarial Text-to-SpeechCode1
Few-Shot Adversarial Prompt Learning on Vision-Language ModelsCode1
White-box Multimodal Jailbreaks Against Large Vision-Language ModelsCode1
Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the WildCode1
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted AttackCode1
Generative Adversarial Text to Image SynthesisCode1
Generating Natural Language Attacks in a Hard Label Black Box SettingCode1
AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion modelsCode1
Adversarial Decoding: Generating Readable Documents for Adversarial ObjectivesCode1
Persistent Anti-Muslim Bias in Large Language ModelsCode1
RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural PromptsCode1
"That Is a Suspicious Reaction!": Interpreting Logits Variation to Detect NLP Adversarial AttacksCode1
A Pilot Study of Query-Free Adversarial Attack against Stable DiffusionCode1
CAT-Gen: Improving Robustness in NLP Models via Controlled Adversarial Text Generation—0
Adversarial Text to Continuous Image Generation—0
Adversarial Text Purification: A Large Language Model Approach for Defense—0
Identifying Adversarial Sentences by Analyzing Text Complexity—0
Adversarial Text Normalization—0
Adversarial Text Generation Without Reinforcement Learning—0
From Unsupervised Machine Translation To Adversarial Text Generation—0
Fooling OCR Systems with Adversarial Text Images—0
PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization—0
IAE: Irony-based Adversarial Examples for Sentiment Analysis Systems—0
Identifying Adversarial Attacks on Text Classifiers—0
Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion—0
A survey on text generation using generative adversarial networks—0
Adversarial Text Generation with Dynamic Contextual Perturbation—0
Adversarial Text Generation via Sequence Contrast Discrimination—0
Don’t Search for a Search Method — Simple Heuristics Suffice for Adversarial Text Attacks—0
FastWordBug: A Fast Method To Generate Adversarial Text Against NLP Applications—0
Don't Search for a Search Method -- Simple Heuristics Suffice for Adversarial Text Attacks—0
Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization—0
AdvCodec: Towards A Unified Framework for Adversarial Text Generation—0
Goal-guided Generative Prompt Injection Attack on Large Language Models—0
Hierarchical Lexical Manifold Projection in Large Language Models: A Novel Mechanism for Multi-Scale Semantic Representation—0
DISCO : efficient unsupervised decoding for discrete natural language problems via convex relaxation—0
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.