Adversarial Text Normalization
Text-based adversarial attacks are becoming more commonplace and accessible to general internet users. As these attacks proliferate, the need to address the gap in model robustness becomes imminent. While retraining on adversarial data may increase performance, there remains an additional class of character-level attacks on which these models falter. Additionally, the process to retrain a model is time and resource intensive, creating a need for a lightweight, reusable defense. In this work, we propose the Adversarial Text Normalizer, a novel method that restores baseline performance on attacked content with low computational overhead. We evaluate the efficacy of the normalizer on two problem areas prone to adversarial attacks, i.e. Hate Speech and Natural Language Inference. We find that text normalization provides a task-agnostic defense against character-level attacks that can be implemented supplementary to adversarial retraining solutions, which are more suited for semantic alterations.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial TextNatural Language InferenceText NormalizationSimilar Papers 제목 키워드 기반
A Domain Agnostic Normalization Layer for Unsupervised Adversarial Domain Adaptation
We propose a normalization layer for unsupervised domain adaption in semantic scene segmentation. Normalization layers are known to improve convergence and generalization and are part of many state-of-the-art fully-convo…
Domain AdaptationScene SegmentationOn Fragile Features and Batch Normalization in Adversarial Training
Modern deep learning architecture utilize batch normalization (BN) to stabilize training and improve accuracy. It has been shown that the BN layers alone are surprisingly expressive. In the context of robustness against …
Adversarial RobustnessGradient Normalization for Generative Adversarial Networks
In this paper, we propose a novel normalization method called gradient normalization (GN) to tackle the training instability of Generative Adversarial Networks (GANs) caused by the sharp gradient space. Unlike existing w…
Aggressive Language Detection with Joint Text Normalization via Adversarial Multi-task Learning
Aggressive language detection (ALD), detecting the abusive and offensive language in texts, is one of the crucial applications in NLP community. Most existing works treat ALD as regular classification with neural models,…
Multi-Task LearningText NormalizationSpectral Normalization for Generative Adversarial Networks
One of the challenges in the study of generative adversarial networks is the instability of its training. In this paper, we propose a novel weight normalization technique called spectral normalization to stabilize the tr…
Image Generation