paper-with-me

Papers

Magnitude-based Neuron Pruning for Backdoor Defens

2024-05-28 · Nan Li, Haoyu Jiang, Ping Yi

Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks, posing concerning threats to their reliable deployment. Recent research reveals that backdoors can be erased from infected DNNs by pruning a specific group of neurons, while how to effectively identify and remove these backdoor-associated neurons remains an open challenge. In this paper, we investigate the correlation between backdoor behavior and neuron magnitude, and find that backdoor neurons deviate from the magnitude-saliency correlation of the model. The deviation inspires us to propose a Magnitude-based Neuron Pruning (MNP) method to detect and prune backdoor neurons. Specifically, MNP uses three magnitude-guided objective functions to manipulate the magnitude-saliency correlation of backdoor neurons, thus achieving the purpose of exposing backdoor behavior, eliminating backdoor neurons and preserving clean neurons, respectively. Experiments show our pruning strategy achieves state-of-the-art backdoor defense performance against a variety of backdoor attacks with a limited amount of clean data, demonstrating the crucial role of magnitude for guiding backdoor defenses.

📄 PDF Abstract BibTeX arXiv:2405.17750

Code (0)

등록된 구현이 없습니다.

Tasks

backdoor defense

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Rethinking Pruning for Backdoor Mitigation: An Optimization Perspective

2024-05-28 · Nan Li, Haiyang Yu, Ping Yi

Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks, posing concerning threats to their reliable deployment. Recent research reveals that backdoors can be erased from infected DNNs by pruning a spe…

backdoor defenseGraph Neural NetworkReinforcement Learning (RL)

Reconstructive Neuron Pruning for Backdoor Defense

2023-05-24 · Yige Li, Xixiang Lyu, Xingjun Ma, Nodens Koren 외

Deep neural networks (DNNs) have been found to be vulnerable to backdoor attacks, raising security concerns about their deployment in mission-critical applications. While existing defense methods have demonstrated promis…

backdoor defense

Defense against Backdoor Attacks via Identifying and Purifying Bad Neurons

2022-08-13 · Mingyuan Fan, Yang Liu, Cen Chen, Ximeng Liu 외

The opacity of neural networks leads their vulnerability to backdoor attacks, where hidden attention of infected neurons is triggered to override normal predictions to the attacker-chosen ones. In this paper, we propose …

backdoor defense

Few-shot Backdoor Defense Using Shapley Estimation

2021-12-30 · CVPR 2022 1 · Jiyang Guan, Zhuozhuo Tu, Ran He, DaCheng Tao

Deep neural networks have achieved impressive performance in a variety of tasks over the last decade, such as autonomous driving, face recognition, and medical diagnosis. However, prior works show that deep neural networ…

Autonomous Drivingbackdoor defenseFace RecognitionMedical Diagnosis

Density-aware Sample-specific Attack

2026-05-27 · Qiyuan Wang, Yao Li, Raymond K. W. Wong arxiv

Despite recent progress in backdoor attacks, existing methods remain susceptible to post-training defenses that erase the backdoor through fine-tuning or pruning. We revisit the core objectives of backdoor attacks and de…

Bilevel Optimization