paper-with-me

Papers

Does Differential Privacy Prevent Backdoor Attacks in Practice?

2023-11-10 · Fereshteh Razmi, Jian Lou, Li Xiong

Differential Privacy (DP) was originally developed to protect privacy. However, it has recently been utilized to secure machine learning (ML) models from poisoning attacks, with DP-SGD receiving substantial attention. Nevertheless, a thorough investigation is required to assess the effectiveness of different DP techniques in preventing backdoor attacks in practice. In this paper, we investigate the effectiveness of DP-SGD and, for the first time in literature, examine PATE in the context of backdoor attacks. We also explore the role of different components of DP algorithms in defending against backdoor attacks and will show that PATE is effective against these attacks due to the bagging structure of the teacher models it employs. Our experiments reveal that hyperparameters and the number of backdoors in the training dataset impact the success of DP algorithms. Additionally, we propose Label-DP as a faster and more accurate alternative to DP-SGD and PATE. We conclude that while Label-DP algorithms generally offer weaker privacy protection, accurate hyper-parameter tuning can make them more effective than DP methods in defending against backdoor attacks while maintaining model accuracy.

📄 PDF Abstract BibTeX arXiv:2311.06227

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Federated Learning in Adversarial Settings

2020-10-15 · Raouf Kerkouche, Gergely Ács, Claude Castelluccia

Federated Learning enables entities to collaboratively learn a shared prediction model while keeping their training data locally. It prevents data collection and aggregation and, therefore, mitigates the associated priva…

Federated LearningQuantization

DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations

2021-03-02 · Eitan Borgnia, Jonas Geiping, Valeriia Cherepanova, Liam Fowl 외

Data poisoning and backdoor attacks manipulate training data to induce security breaches in a victim model. These attacks can be provably deflected using differentially private (DP) training methods, although this comes …

Data Poisoning

Robust Anomaly Detection and Backdoor Attack Detection Via Differential Privacy

2019-11-16 · ICLR 2020 1 · Min Du, Ruoxi Jia, Dawn Song

Outlier detection and novelty detection are two important topics for anomaly detection. Suppose the majority of a dataset are drawn from a certain distribution, outlier detection and novelty detection both aim to detect …

Anomaly DetectionBackdoor AttackNovelty DetectionOutlier Detection

Local and Central Differential Privacy for Robustness and Privacy in Federated Learning

2020-09-08 · Mohammad Naseri, Jamie Hayes, Emiliano De Cristofaro

Federated Learning (FL) allows multiple participants to train machine learning models collaboratively by keeping their datasets local while only exchanging model updates. Alas, this is not necessarily free from privacy a…

Federated Learning

BEAS: Blockchain Enabled Asynchronous & Secure Federated Machine Learning

2022-02-06 · Arup Mondal, Harpreet Virk, Debayan Gupta

Federated Learning (FL) enables multiple parties to distributively train a ML model without revealing their private datasets. However, it assumes trust in the centralized aggregator which stores and aggregates model upda…

Anomaly DetectionBIG-bench Machine LearningData PoisoningFederated Learning+1