TextShield: Beyond Successfully Detecting Adversarial Sentences in Text Classification
Adversarial attack serves as a major challenge for neural network models in NLP, which precludes the model's deployment in safety-critical applications. A recent line of work, detection-based defense, aims to distinguish adversarial sentences from benign ones. However, {the core limitation of previous detection methods is being incapable of giving correct predictions on adversarial sentences unlike defense methods from other paradigms.} To solve this issue, this paper proposes TextShield: (1) we discover a link between text attack and saliency information, and then we propose a saliency-based detector, which can effectively detect whether an input sentence is adversarial or not. (2) We design a saliency-based corrector, which converts the detected adversary sentences to benign ones. By combining the saliency-based detector and corrector, TextShield extends the detection-only paradigm to a detection-correction paradigm, thus filling the gap in the existing detection-based defense. Comprehensive experiments show that (a) TextShield consistently achieves higher or comparable performance than state-of-the-art defense methods across various attacks on different benchmarks. (b) our saliency-based detector outperforms existing detectors for detecting adversarial sentences.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackClassificationSentencetext-classificationText ClassificationSimilar Papers 제목 키워드 기반
TextShield-R1: Reinforced Reasoning for Tampered Text Detection
The growing prevalence of tampered images poses serious security threats, highlighting the urgent need for reliable detection methods. Multimodal large language models (MLLMs) demonstrate strong potential in analyzing ta…
Reinforcement LearningText DetectionDetecting and Defending Against Adversarial Attacks on Automatic Speech Recognition via Diffusion Models
Automatic speech recognition (ASR) systems are known to be vulnerable to adversarial attacks. This paper addresses detection and defence against targeted white-box attacks on speech signals for ASR systems. While existin…
Adversarial AttackAdversarial PurificationAutomatic Speech RecognitionSpeech RecognitionEFSG: Evolutionary Fooling Sentences Generator
Large pre-trained language representation models (LMs) have recently collected a huge number of successes in many NLP tasks. In 2018 BERT, and later its successors (e.g. RoBERTa), obtained state-of-the-art results in cla…
Adversarial AttackBinary ClassificationCoLAData Augmentation+1Detecting Adversarial Examples in Batches -- a geometrical approach
Many deep learning methods have successfully solved complex tasks in computer vision and speech recognition applications. Nonetheless, the robustness of these models has been found to be vulnerable to perturbed inputs or…
Adversarial AttackAdversarial Attack DetectionImage ClassificationMaking Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training
Although attention mechanisms have become fundamental components of deep learning models, they are vulnerable to perturbations, which may degrade the prediction performance and model interpretability. Adversarial trainin…
Semi-Supervised Text Classificationtext-classificationText Classification