paper-with-me

Papers

NCL: Textual Backdoor Defense Using Noise-augmented Contrastive Learning

2023-03-03 · Shengfang Zhai, Qingni Shen, Xiaoyi Chen, Weilong Wang, Cong Li, Yuejian Fang, Zhonghai Wu

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.

📄 PDF Abstract BibTeX arXiv:2303.01742

Code (0)

등록된 구현이 없습니다.

Tasks

backdoor defenseContrastive Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning

2023-11-20 · CVPR 2024 1 · Siyuan Liang, Mingli Zhu, Aishan Liu, Baoyuan Wu 외

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 Learning

Adversarial Backdoor Defense in CLIP

2024-09-24 · Junhao Kuang, Siyuan Liang, Jiawei Liang, Kuanrong Liu 외

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 Augmentation

On the Difficulty of Defending Contrastive Learning against Backdoor Attacks

2023-12-14 · Changjiang Li, Ren Pang, Bochuan Cao, Zhaohan Xi 외

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 Learning

CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning

2024-09-26 · Yuan Xun, Siyuan Liang, Xiaojun Jia, Xinwei Liu 외

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+2

From Shortcuts to Triggers: Backdoor Defense with Denoised PoE

2023-05-24 · Qin Liu, Fei Wang, Chaowei Xiao, Muhao Chen

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