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.
StealthRank: LLM Ranking Manipulation via Stealthy Prompt Optimization
Breaking BERT: Gradient Attack on Twitter Sentiment Analysis for Targeted Misclassification
A Grey-box Text Attack Framework using Explainable AI
Continuous Adversarial Text Representation Learning for Affective Recognition
SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation
Hierarchical Lexical Manifold Projection in Large Language Models: A Novel Mechanism for Multi-Scale Semantic Representation
EMPRA: Embedding Perturbation Rank Attack against Neural Ranking Models
Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization
BinarySelect to Improve Accessibility of Black-Box Attack Research
PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization
TSCheater: Generating High-Quality Tibetan Adversarial Texts via Visual Similarity
SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments
NMT-Obfuscator Attack: Ignore a sentence in translation with only one word
IAE: Irony-based Adversarial Examples for Sentiment Analysis Systems
Target-driven Attack for Large Language Models
AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models
Graded Suspiciousness of Adversarial Texts to Human
Adversarial Decoding: Generating Readable Documents for Adversarial Objectives
Vision-fused Attack: Advancing Aggressive and Stealthy Adversarial Text against Neural Machine Translation
OpenFact at CheckThat! 2024: Combining Multiple Attack Methods for Effective Adversarial Text Generation
Adversarial Text Rewriting for Text-aware Recommender Systems
Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion
Enhancing Adversarial Text Attacks on BERT Models with Projected Gradient Descent
Dissecting Adversarial Robustness of Multimodal LM Agents
Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?
Phantom: General Trigger Attacks on Retrieval Augmented Language Generation
White-box Multimodal Jailbreaks Against Large Vision-Language Models
R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model
Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective
Semantic Stealth: Adversarial Text Attacks on NLP Using Several Methods
Goal-guided Generative Prompt Injection Attack on Large Language Models
Few-Shot Adversarial Prompt Learning on Vision-Language Models
Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory
A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models
Arabic Synonym BERT-based Adversarial Examples for Text Classification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.