paper-with-me

Papers

Backdoor Defense with Machine Unlearning

2022-01-24 · Yang Liu, Mingyuan Fan, Cen Chen, Ximeng Liu, Zhuo Ma, Li Wang, Jianfeng Ma

Backdoor injection attack is an emerging threat to the security of neural networks, however, there still exist limited effective defense methods against the attack. In this paper, we propose BAERASE, a novel method that can erase the backdoor injected into the victim model through machine unlearning. Specifically, BAERASE mainly implements backdoor defense in two key steps. First, trigger pattern recovery is conducted to extract the trigger patterns infected by the victim model. Here, the trigger pattern recovery problem is equivalent to the one of extracting an unknown noise distribution from the victim model, which can be easily resolved by the entropy maximization based generative model. Subsequently, BAERASE leverages these recovered trigger patterns to reverse the backdoor injection procedure and induce the victim model to erase the polluted memories through a newly designed gradient ascent based machine unlearning method. Compared with the previous machine unlearning solutions, the proposed approach gets rid of the reliance on the full access to training data for retraining and shows higher effectiveness on backdoor erasing than existing fine-tuning or pruning methods. Moreover, experiments show that BAERASE can averagely lower the attack success rates of three kinds of state-of-the-art backdoor attacks by 99\% on four benchmark datasets.

📄 PDF Abstract BibTeX arXiv:2201.09538

Code (0)

등록된 구현이 없습니다.

Tasks

backdoor defenseMachine Unlearning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

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

ReVeil: Unconstrained Concealed Backdoor Attack on Deep Neural Networks using Machine Unlearning

2025-02-17 · Manaar Alam, Hithem Lamri, Michail Maniatakos

Backdoor attacks embed hidden functionalities in deep neural networks (DNN), triggering malicious behavior with specific inputs. Advanced defenses monitor anomalous DNN inferences to detect such attacks. However, conceal…

Backdoor AttackMachine Unlearning

Exploiting Machine Unlearning for Backdoor Attacks in Deep Learning System

2023-09-12 · Peixin Zhang, Jun Sun, Mingtian Tan, Xinyu Wang

In recent years, the security issues of artificial intelligence have become increasingly prominent due to the rapid development of deep learning research and applications. Backdoor attack is an attack targeting the vulne…

Backdoor AttackDeep LearningMachine Unlearning

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models

2025-01-05 · Peihai Jiang, Xixiang Lyu, Yige Li, Jing Ma

Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulnerable to backdoor attacks, where even a …

backdoor defense

Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness

2024-05-30 · Weilin Lin, Li Liu, Shaokui Wei, Jianze Li 외

The security threat of backdoor attacks is a central concern for deep neural networks (DNNs). Recently, without poisoned data, unlearning models with clean data and then learning a pruning mask have contributed to backdo…

backdoor defense