paper-with-me

홈 › Papers

Backdoor Defense through Self-Supervised and Generative Learning

2024-09-02 · Ivan Sabolić, Ivan Grubišić, Siniša Šegvić

Backdoor attacks change a small portion of training data by introducing hand-crafted triggers and rewiring the corresponding labels towards a desired target class. Training on such data injects a backdoor which causes malicious inference in selected test samples. Most defenses mitigate such attacks through various modifications of the discriminative learning procedure. In contrast, this paper explores an approach based on generative modelling of per-class distributions in a self-supervised representation space. Interestingly, these representations get either preserved or heavily disturbed under recent backdoor attacks. In both cases, we find that per-class generative models allow to detect poisoned data and cleanse the dataset. Experiments show that training on cleansed dataset greatly reduces the attack success rate and retains the accuracy on benign inputs.

📄 PDF Abstract BibTeX arXiv:2409.01185

Code (0)

등록된 구현이 없습니다.

Tasks

backdoor defense

Similar Papers 제목 키워드 기반

Backdoor Attacks in the Supply Chain of Masked Image Modeling

2022-10-04 · Xinyue Shen, Xinlei He, Zheng Li, Yun Shen 외

Masked image modeling (MIM) revolutionizes self-supervised learning (SSL) for image pre-training. In contrast to previous dominating self-supervised methods, i.e., contrastive learning, MIM attains state-of-the-art perfo…

Contrastive LearningSelf-Supervised Learning

Towards Understanding How Self-training Tolerates Data Backdoor Poisoning

2023-01-20 · Soumyadeep Pal, Ren Wang, Yuguang Yao, Sijia Liu

Recent studies on backdoor attacks in model training have shown that polluting a small portion of training data is sufficient to produce incorrect manipulated predictions on poisoned test-time data while maintaining high…

backdoor defenseRepresentation Learning

DEFUSE: Generalizable Backdoor Defense for Self-Supervised Encoders with Generative Priors

2026-08-26 · Tuo Chen, Jie Gui, Minjing Dong, Lanting Fang 외 arxiv

Self-supervised learning (SSL) encoders are vulnerable to backdoor attacks, posing threats to both visual SSL encoders and vision-language encoders. Existing defenses are typically designed for only one of these paradigm…

Self-Supervised Learning

BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning

2021-08-01 · Jinyuan Jia, Yupei Liu, Neil Zhenqiang Gong

Self-supervised learning in computer vision aims to pre-train an image encoder using a large amount of unlabeled images or (image, text) pairs. The pre-trained image encoder can then be used as a feature extractor to bui…

Backdoor AttackSelf-Supervised Learning

Towards Imperceptible Backdoor Attack in Self-supervised Learning

2024-05-23 · Hanrong Zhang, Zhenting Wang, Tingxu Han, Mingyu Jin 외

Self-supervised learning models are vulnerable to backdoor attacks. Existing backdoor attacks that are effective in self-supervised learning often involve noticeable triggers, like colored patches, which are vulnerable t…

Backdoor AttackSelf-Supervised Learning