How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacks
원문 초록
Natural Language Processing (NLP) models based on Machine Learning (ML) are susceptible to adversarial attacks -- malicious algorithms that imperceptibly modify input text to force models into making incorrect predictions. However, evaluations of these attacks ignore the property of imperceptibility or study it under limited settings. This entails that adversarial perturbations would not pass any human quality gate and do not represent real threats to human-checked NLP systems. To bypass this limitation and enable proper assessment (and later, improvement) of NLP model robustness, we have surveyed 378 human participants about the perceptibility of text adversarial examples produced by state-of-the-art methods. Our results underline that existing text attacks are impractical in real-world scenarios where humans are involved. This contrasts with previous smaller-scale human studies, which reported overly optimistic conclusions regarding attack success. Through our work, we hope to position human perceptibility as a first-class success criterion for text attacks, and provide guidance for research to build effective attack algorithms and, in turn, design appropriate defence mechanisms.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
StealthRank: LLM Ranking Manipulation via Stealthy Prompt Optimization
Breaking BERT: Gradient Attack on Twitter Sentiment Analysis for Targeted Misclassification
SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation
EMPRA: Embedding Perturbation Rank Attack against Neural Ranking Models
BinarySelect to Improve Accessibility of Black-Box Attack Research
TSCheater: Generating High-Quality Tibetan Adversarial Texts via Visual Similarity
토론
이 논문과 연결된 포럼 글이 아직 없습니다.