Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer
Adversarial attacks and backdoor attacks are two common security threats that hang over deep learning. Both of them harness task-irrelevant features of data in their implementation. Text style is a feature that is naturally irrelevant to most NLP tasks, and thus suitable for adversarial and backdoor attacks. In this paper, we make the first attempt to conduct adversarial and backdoor attacks based on text style transfer, which is aimed at altering the style of a sentence while preserving its meaning. We design an adversarial attack method and a backdoor attack method, and conduct extensive experiments to evaluate them. Experimental results show that popular NLP models are vulnerable to both adversarial and backdoor attacks based on text style transfer -- the attack success rates can exceed 90% without much effort. It reflects the limited ability of NLP models to handle the feature of text style that has not been widely realized. In addition, the style transfer-based adversarial and backdoor attack methods show superiority to baselines in many aspects. All the code and data of this paper can be obtained at https://github.com/thunlp/StyleAttack.
Code (1)
Tasks
Adversarial AttackBackdoor AttackSentenceStyle TransferText Style TransferSimilar Papers 제목 키워드 기반
Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifiers
Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are c…
Kallima: A Clean-label Framework for Textual Backdoor Attacks
Although Deep Neural Network (DNN) has led to unprecedented progress in various natural language processing (NLP) tasks, research shows that deep models are extremely vulnerable to backdoor attacks. The existing backdoor…
Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation
Text-to-image diffusion models have revolutionized generative AI, but their vulnerability to backdoor attacks poses significant security risks. Adversaries can inject imperceptible textual triggers into training data, ca…
Knowledge DistillationDoes Adversarial Robustness Really Imply Backdoor Vulnerability?
Recent research has revealed a trade-off between the robustness against adversarial attacks and backdoor attacks. Specifically, with the increasing adversarial robustness obtained through adversarial training, the model …
Adversarial RobustnessNatural Backdoor Attack on Text Data
Recently, advanced NLP models have seen a surge in the usage of various applications. This raises the security threats of the released models. In addition to the clean models' unintentional weaknesses, {\em i.e.,} advers…
Backdoor Attacktext-classificationText Classification