Regularization Helps with Mitigating Poisoning Attacks: Distributionally-Robust Machine Learning Using the Wasserstein Distance
We use distributionally-robust optimization for machine learning to mitigate the effect of data poisoning attacks. We provide performance guarantees for the trained model on the original data (not including the poison records) by training the model for the worst-case distribution on a neighbourhood around the empirical distribution (extracted from the training dataset corrupted by a poisoning attack) defined using the Wasserstein distance. We relax the distributionally-robust machine learning problem by finding an upper bound for the worst-case fitness based on the empirical sampled-averaged fitness and the Lipschitz-constant of the fitness function (on the data for given model parameters) as regularizer. For regression models, we prove that this regularizer is equal to the dual norm of the model parameters. We use the Wine Quality dataset, the Boston Housing Market dataset, and the Adult dataset for demonstrating the results of this paper.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningData PoisoningSimilar Papers 제목 키워드 기반
Mitigating Data Poisoning in Text Classification with Differential Privacy
NLP models are vulnerable to data poisoning attacks. One type of attack can plant a backdoor in a model by injecting poisoned examples in training, causing the victim model to misclassify test instances which include a s…
ClassificationData Poisoningtext-classificationText ClassificationSystematic Evaluation of Backdoor Data Poisoning Attacks on Image Classifiers
Backdoor data poisoning attacks have recently been demonstrated in computer vision research as a potential safety risk for machine learning (ML) systems. Traditional data poisoning attacks manipulate training data to ind…
Data PoisoningRegularization Can Help Mitigate Poisoning Attacks... with the Right Hyperparameters
Machine learning algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to degrade the algorithms' performance. We show that current approaches, which typically assume that r…
Bilevel OptimizationregressionMitigating Malicious Attacks in Federated Learning via Confidence-aware Defense
Federated Learning (FL) is a distributed machine learning diagram that enables multiple clients to collaboratively train a global model without sharing their private local data. However, FL systems are vulnerable to atta…
Data PoisoningFederated LearningModel PoisoningSparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification
Federated learning is inherently vulnerable to model poisoning attacks because its decentralized nature allows attackers to participate with compromised devices. In model poisoning attacks, the attacker reduces the model…
Federated LearningModel Poisoning