.png){kind=icon}
返回
AdvChar: Attacking Interpretable NLP Systems
.png){kind=icon}
PRE
AI
DOI：10.1109/TIFS.2025.3622073.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Studies have shown that machine learning systems are vulnerable to adversarial examples in theory and practice. Where previous attacks have focused mainly on visual models that exploit the difference between human and machine perception, text-based models have also fallen victim to these attacks. However, these attacks often fail to maintain the semantic meaning of the text and similarity. This paper introduces AdvChar, a black-box attack on Interpretable Natural Language Processing Systems, designed to mislead the classifier while keeping the interpretation similar to benign inputs, thus exploiting trust in system transparency. AdvChar achieves this by making less noticeable modifications to text input, forcing the deep learning classifier to make incorrect predictions and preserve the original interpretation. We use an interpretation-focused scoring approach to determine the most critical tokens that, when changed, can cause the classifier to misclassify the input. We apply simple character-level modifications to measure the importance of tokens, minimizing the difference between the original and new text while generating adversarial interpretations similar to benign ones. We thoroughly evaluated AdvChar by testing it against seven NLP models and three interpretation models using benchmark datasets for the classification task. Our experiments show that AdvChar can significantly reduce the prediction accuracy of current deep learning models by altering just two characters on average in input samples.
Keyword:
Deep learning
Perturbation methods
Natural language processing
Text categorization
Closed box
Robustness
Predictive models
Decision making
Computer science
Vectors
Adversarial machine learning
interpretable deep learning
black-box attacks
NLP
期刊
IF:
8
论文数:
5.3K
被引数:
2.3W
机构
引用论文
分享收藏Enhancing Model Robustness by Incorporating Adversarial Knowledge into Semantic Representation.png)
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
OAAI
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)IF0
OAAI分享收藏NUAT-GAN: Generating Black-Box Natural Universal Adversarial Triggers for Text Classifiers Using Generative Adversarial NetworksNuat-gan: 使用生成对抗网络为文本分类器生成黑盒自然通用对抗触发器
PREAI
分享收藏分享收藏分享收藏分享收藏Recent advances in deep learning based dialogue systems: a systematic survey基于深度学习的对话系统的最新进展: 系统综述
PREAI
分享收藏
查看更多内容