paper-with-me

홈 › Papers

Backdoor Defense via Suppressing Model Shortcuts

2022-11-02 · Sheng Yang, Yiming Li, Yong Jiang, Shu-Tao Xia

Recent studies have demonstrated that deep neural networks (DNNs) are vulnerable to backdoor attacks during the training process. Specifically, the adversaries intend to embed hidden backdoors in DNNs so that malicious model predictions can be activated through pre-defined trigger patterns. In this paper, we explore the backdoor mechanism from the angle of the model structure. We select the skip connection for discussions, inspired by the understanding that it helps the learning of model `shortcuts' where backdoor triggers are usually easier to be learned. Specifically, we demonstrate that the attack success rate (ASR) decreases significantly when reducing the outputs of some key skip connections. Based on this observation, we design a simple yet effective backdoor removal method by suppressing the skip connections in critical layers selected by our method. We also implement fine-tuning on these layers to recover high benign accuracy and to further reduce ASR. Extensive experiments on benchmark datasets verify the effectiveness of our method.

📄 PDF Abstract BibTeX arXiv:2211.05631

Code (1)

20000yshust/Backdoor-Defense-Via-Suppressing-Model-Shortcuts 공식 구현 pytorch

Tasks

backdoor defensemodel

Similar Papers 제목 키워드 기반

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

A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models

2026-04-06 · Tianmeng Fang, Yong Wang, Zetai Kong, Zengzhen Su 외 arxiv

Multimodal large language models have become an important infrastructure for unified processing of visual and linguistic tasks. However, such models are highly susceptible to backdoor implantation during supervised fine-…

Data AugmentationText Generation

Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats

2024-09-29 · Kuanrong Liu, Siyuan Liang, Jiawei Liang, Pengwen Dai 외

Multimodal contrastive learning uses various data modalities to create high-quality features, but its reliance on extensive data sources on the Internet makes it vulnerable to backdoor attacks. These attacks insert malic…

Backdoor Attackbackdoor defenseContrastive LearningMachine Unlearning

Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor

2024-05-25 · Shaokui Wei, Hongyuan Zha, Baoyuan Wu

Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In this paper, we focus on in-training back…

Backdoor Attackbackdoor defenseData Poisoning

Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks

2024-01-27 · Yige Li, Jiabo He, Hanxun Huang, Jun Sun 외

Backdoor attacks have become a significant threat to the pre-training and deployment of deep neural networks (DNNs). Although numerous methods for detecting and mitigating backdoor attacks have been proposed, most rely o…