A Simple Yet Efficient Method for Adversarial Word-Substitute Attack
NLP researchers propose different word-substitute black-box attacks that can fool text classification models. In such attack, an adversary keeps sending crafted adversarial queries to the target model until it can successfully achieve the intended outcome. State-of-the-art attack methods usually require hundreds or thousands of queries to find one adversarial example. In this paper, we study whether a sophisticated adversary can attack the system with much less queries. We propose a simple yet efficient method that can reduce the average number of adversarial queries by 3-30 times and maintain the attack effectiveness. This research highlights that an adversary can fool a deep NLP model with much less cost.
Code (0)
등록된 구현이 없습니다.
Tasks
text-classificationText ClassificationSimilar Papers 제목 키워드 기반
HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models
Black-box adversarial attack on vision-language pre-trained models is a practical and challenging task, as text and image perturbations need to be considered simultaneously, and only the predicted results are accessible.…
Contrastive LearningAdversarial AttackGenerating Adversarial Examples in Chinese Texts Using Sentence-Pieces
Adversarial attacks in texts are mostly substitution-based methods that replace words or characters in the original texts to achieve success attacks. Recent methods use pre-trained language models as the substitutes gene…
Language ModelingLanguage ModellingSentenceActive Learning for Black-Box Adversarial Attacks in EEG-Based Brain-Computer Interfaces
Deep learning has made significant breakthroughs in many fields, including electroencephalogram (EEG) based brain-computer interfaces (BCIs). However, deep learning models are vulnerable to adversarial attacks, in which …
Active LearningDeep LearningEEGElectroencephalogram (EEG)HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text
Black-box hard-label adversarial attack on text is a practical and challenging task, as the text data space is inherently discrete and non-differentiable, and only the predicted label is accessible. Research on this prob…
Adversarial AttackHard-label AttackNatural Language InferenceSemantic Similarity+3Adv-OLM: Generating Textual Adversaries via OLM
Deep learning models are susceptible to adversarial examples that have imperceptible perturbations in the original input, resulting in adversarial attacks against these models. Analysis of these attacks on the state of t…
Sentencetext-classificationText Classification