Is feature selection secure against training data poisoning?
Learning in adversarial settings is becoming an important task for application domains where attackers may inject malicious data into the training set to subvert normal operation of data-driven technologies. Feature selection has been widely used in machine learning for security applications to improve generalization and computational efficiency, although it is not clear whether its use may be beneficial or even counterproductive when training data are poisoned by intelligent attackers. In this work, we shed light on this issue by providing a framework to investigate the robustness of popular feature selection methods, including LASSO, ridge regression and the elastic net. Our results on malware detection show that feature selection methods can be significantly compromised under attack (we can reduce LASSO to almost random choices of feature sets by careful insertion of less than 5% poisoned training samples), highlighting the need for specific countermeasures.
Code (0)
등록된 구현이 없습니다.
Tasks
Computational EfficiencyData Poisoningfeature selectionMalware DetectionSimilar Papers 제목 키워드 기반
Fuzzy Feature Selection with Key-based Cryptographic Transformations
In the field of cryptography, the selection of relevant features plays a crucial role in enhancing the security and efficiency of cryptographic algorithms. This paper presents a novel approach of applying fuzzy feature s…
feature selectionBlockchain-based Secure Client Selection in Federated Learning
Despite the great potential of Federated Learning (FL) in large-scale distributed learning, the current system is still subject to several privacy issues due to the fact that local models trained by clients are exposed t…
Federated LearningPrivacy-Preserving Feature Selection with Secure Multiparty Computation
Existing work on privacy-preserving machine learning with Secure Multiparty Computation (MPC) is almost exclusively focused on model training and on inference with trained models, thereby overlooking the important data p…
BIG-bench Machine Learningfeature selectionPrivacy PreservingSecureLearn -- An Attack-agnostic Defense for Multiclass Machine Learning Against Data Poisoning Attacks
Data poisoning attacks are a potential threat to machine learning (ML) models, aiming to manipulate training datasets to disrupt their performance. Existing defenses are mostly designed to mitigate specific poisoning att…
Adversarial RobustnessAdRo-FL: Informed and Secure Client Selection for Federated Learning in the Presence of Adversarial Aggregator
Federated Learning (FL) enables collaborative learning without exposing clients' data. While clients only share model updates with the aggregator, studies reveal that aggregators can infer sensitive information from thes…
Federated LearningPrivacy Preserving