Preserving Semantics in Textual Adversarial Attacks
The growth of hateful online content, or hate speech, has been associated with a global increase in violent crimes against minorities [23]. Harmful online content can be produced easily, automatically and anonymously. Even though, some form of auto-detection is already achieved through text classifiers in NLP, they can be fooled by adversarial attacks. To strengthen existing systems and stay ahead of attackers, we need better adversarial attacks. In this paper, we show that up to 70% of adversarial examples generated by adversarial attacks should be discarded because they do not preserve semantics. We address this core weakness and propose a new, fully supervised sentence embedding technique called Semantics-Preserving-Encoder (SPE). Our method outperforms existing sentence encoders used in adversarial attacks by achieving 1.2x - 5.1x better real attack success rate. We release our code as a plugin that can be used in any existing adversarial attack to improve its quality and speed up its execution.
Code (1)
Tasks
Adversarial AttackSentenceSentence EmbeddingSentence-EmbeddingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Semantics Preserving Adversarial Attacks
While progress has been made in crafting visually imperceptible adversarial examples, constructing semantically meaningful ones remains a challenge. In this paper, we propose a framework to generate semantics preserving …
Model Robustness with Text Classification: Semantic-preserving adversarial attacks
We propose algorithms to create adversarial attacks to assess model robustness in text classification problems. They can be used to create white box attacks and black box attacks while at the same time preserving the sem…
Adversarial AttackClassificationGeneral Classificationtext-classification+1Semantics Preserving Adversarial Learning
While progress has been made in crafting visually imperceptible adversarial examples, constructing semantically meaningful ones remains a challenge. In this paper, we propose a framework to generate semantics preserving …
Text ClassificationDefensive Dual Masking for Robust Adversarial Defense
The field of textual adversarial defenses has gained considerable attention in recent years due to the increasing vulnerability of natural language processing (NLP) models to adversarial attacks, which exploit subtle per…
Adversarial DefenseDeceiving Question-Answering Models: A Hybrid Word-Level Adversarial Approach
Deep learning underpins most of the currently advanced natural language processing (NLP) tasks such as textual classification, neural machine translation (NMT), abstractive summarization and question-answering (QA). Howe…
Abstractive Text SummarizationMachine TranslationNMTQuestion Answering