Papers with Code 아카이브
Adversarial Text
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples
Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the Wild
End-to-End Adversarial Text-to-Speech
Improving Adversarial Text Generation by Modeling the Distant Future
TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP
BAE: BERT-based Adversarial Examples for Text Classification
Meta-CoTGAN: A Meta Cooperative Training Paradigm for Improving Adversarial Text Generation
Generating Natural Language Adversarial Examples on a Large Scale with Generative Models
Playing to Learn Better: Repeated Games for Adversarial Learning with Multiple Classifiers
FastWordBug: A Fast Method To Generate Adversarial Text Against NLP Applications
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack
Identifying Adversarial Sentences by Analyzing Text Complexity
Universal Adversarial Perturbation for Text Classification
Evaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial Examples
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment
TextBugger: Generating Adversarial Text Against Real-world Applications
Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classification
Adversarial Text Generation Without Reinforcement Learning
SALSA-TEXT : self attentive latent space based adversarial text generation
Adversarial Text Generation via Feature-Mover's Distance
Fooling OCR Systems with Adversarial Text Images
Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers
DANCin SEQ2SEQ: Fooling Text Classifiers with Adversarial Text Example Generation
Towards Crafting Text Adversarial Samples
Generative Adversarial Text to Image Synthesis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.