Regularization 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 regularization hyperparameters remain constant, lead to an overly pessimistic view of the algorithms' robustness and of the impact of regularization. We propose a novel optimal attack formulation that considers the effect of the attack on the hyperparameters, modelling the attack as a \emph{minimax bilevel optimization problem}. This allows to formulate optimal attacks, select hyperparameters and evaluate robustness under worst case conditions. We apply this formulation to logistic regression using $L_2$ regularization, empirically show the limitations of previous strategies and evidence the benefits of using $L_2$ regularization to dampen the effect of poisoning attacks.
Code (0)
등록된 구현이 없습니다.
Tasks
Bilevel OptimizationregressionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
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 re…
BIG-bench Machine LearningData PoisoningRegularisation Can Mitigate Poisoning Attacks: A Novel Analysis Based on Multiobjective Bilevel Optimisation
Machine Learning (ML) algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to deliberately degrade the algorithms' performance. Optimal poisoning attacks, which can be form…
Bilevel OptimizationData PoisoningL2 RegularizationMultiobjective OptimizationHyperparameter Learning under Data Poisoning: Analysis of the Influence of Regularization via Multiobjective Bilevel Optimization
Machine Learning (ML) algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to deliberately degrade the algorithms' performance. Optimal attacks can be formulated as bilevel…
Bilevel OptimizationData PoisoningCopyrightShield: Spatial Similarity Guided Backdoor Defense against Copyright Infringement in Diffusion Models
The diffusion model has gained significant attention due to its remarkable data generation ability in fields such as image synthesis. However, its strong memorization and replication abilities with respect to the trainin…
backdoor defenseImage GenerationMemorizationSystematic 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 Poisoning