NCL: Textual Backdoor Defense Using Noise-augmented Contrastive Learning
At present, backdoor attacks attract attention as they do great harm to deep learning models. The adversary poisons the training data making the model being injected with a backdoor after being trained unconsciously by victims using the poisoned dataset. In the field of text, however, existing works do not provide sufficient defense against backdoor attacks. In this paper, we propose a Noise-augmented Contrastive Learning (NCL) framework to defend against textual backdoor attacks when training models with untrustworthy data. With the aim of mitigating the mapping between triggers and the target label, we add appropriate noise perturbing possible backdoor triggers, augment the training dataset, and then pull homology samples in the feature space utilizing contrastive learning objective. Experiments demonstrate the effectiveness of our method in defending three types of textual backdoor attacks, outperforming the prior works.
Code (0)
등록된 구현이 없습니다.
Tasks
backdoor defenseContrastive LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
Studying backdoor attacks is valuable for model copyright protection and enhancing defenses. While existing backdoor attacks have successfully infected multimodal contrastive learning models such as CLIP, they can be eas…
Backdoor AttackContrastive LearningAdversarial Backdoor Defense in CLIP
Multimodal contrastive pretraining, exemplified by models like CLIP, has been found to be vulnerable to backdoor attacks. While current backdoor defense methods primarily employ conventional data augmentation to create a…
backdoor defenseData AugmentationOn the Difficulty of Defending Contrastive Learning against Backdoor Attacks
Recent studies have shown that contrastive learning, like supervised learning, is highly vulnerable to backdoor attacks wherein malicious functions are injected into target models, only to be activated by specific trigge…
Contrastive LearningCleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning
Pre-trained large models for multimodal contrastive learning, such as CLIP, have been widely recognized in the industry as highly susceptible to data-poisoned backdoor attacks. This poses significant risks to downstream …
backdoor defenseContrastive LearningcounterfactualText Augmentation+2From Shortcuts to Triggers: Backdoor Defense with Denoised PoE
Language models are often at risk of diverse backdoor attacks, especially data poisoning. Thus, it is important to investigate defense solutions for addressing them. Existing backdoor defense methods mainly focus on back…
backdoor defenseData PoisoningDenoisingSentence+1