Data to 7 Oct 2026

Is feature selection secure against training data poisoning?

arXiv 1804.07933 ↗First posted 21 Apr 2018cs.LG cs.CR cs.GTcited by 88

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 88 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 28; 2022: 16; 2023: 18; 2024: 11; 2025: 10; 2026: 4.

88 papers.

Sort:

By area:

2023Poisoning Web-Scale Training Datasets is Practicalcited by 276
2021SPECTRE: Defending Against Backdoor Attacks Using Robust Statisticscited by 123
2021Adversarial Examples Make Strong Poisonscited by 115
2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
2022Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protectioncited by 80
2019Policy Poisoning in Batch Reinforcement Learning and Controlcited by 70
2021Robust and Differentially Private Mean Estimationcited by 66
2021Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Trainingcited by 58
2021Undistillable: Making A Nasty Teacher That CANNOT teach studentscited by 36
2021Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Releasecited by 35
2021DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentationscited by 33
2022Identifying a Training-Set Attack's Target Using Renormalized Influence Estimationcited by 32

38 more

2022SNAP: Efficient Extraction of Private Properties with Poisoningcited by 29
2022AI Security for Geoscience and Remote Sensing: Challenges and Future Trendscited by 23
2021Defense Against Reward Poisoning Attacks in Reinforcement Learningcited by 20
2022BagFlip: A Certified Defense against Data Poisoningcited by 18
2024Purify Unlearnable Examples via Rate-Constrained Variational Autoencoderscited by 18
2023Towards more Practical Threat Models in Artificial Intelligence Securitycited by 17
2023FLShield: A Validation Based Federated Learning Framework to Defend Against Poisoning Attackscited by 15
2023Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attackscited by 14
2021Data Poisoning Attacks and Defenses to Crowdsourcing Systemscited by 12
2022Can Adversarial Training Be Manipulated By Non-Robust Features?cited by 12
2023Robust Nonparametric Regression under Poisoning Attackcited by 11
2025MTL-UE: Learning to Learn Nothing for Multi-Task Learningcited by 11
2021Accumulative Poisoning Attacks on Real-time Datacited by 10
2021Going Grayscale: The Road to Understanding and Improving Unlearnable Examplescited by 10
2022What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradictioncited by 10
2023Backdoor Attacks in Peer-to-Peer Federated Learningcited by 9
2023Client-specific Property Inference against Secure Aggregation in Federated Learningcited by 9
2021Regularization Can Help Mitigate Poisoning Attacks... with the Right Hyperparameterscited by 8
2022ScionFL: Efficient and Robust Secure Quantized Aggregationcited by 8
2021Adversarial Attacks and Defenses in Physiological Computing: A Systematic Reviewcited by 7
2021Machine Learning for Security in Vehicular Networks: A Comprehensive Surveycited by 7
2024Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignmentcited by 7
2021Turning Federated Learning Systems Into Covert Channelscited by 6
2021Evaluating the Cybersecurity Risk of Real World, Machine Learning Production Systemscited by 6
2021FooBaR: Fault Fooling Backdoor Attack on Neural Network Trainingcited by 6
2022Careful What You Wish For: on the Extraction of Adversarially Trained Modelscited by 6
2025StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusionscited by 6
2022FairRoad: Achieving Fairness for Recommender Systems with Optimized Antidote Datacited by 5
2024Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attackscited by 5
2024Learning to Obstruct Few-Shot Image Classification over Restricted Classescited by 5
2025No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanismscited by 5
2022Backdoors Stuck At The Frontdoor: Multi-Agent Backdoor Attacks That Backfirecited by 4
2023Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Triggercited by 4
2024Corruption-Robust Offline Two-Player Zero-Sum Markov Gamescited by 4
2024Data Poisoning Attacks in Intelligent Transportation Systems: A Surveycited by 4
2021Widen The Backdoor To Let More Attackers Incited by 3
2023Protecting Federated Learning from Extreme Model Poisoning Attacks via Multidimensional Time Series Anomaly Detectioncited by 3
2023Hyperparameter Learning under Data Poisoning: Analysis of the Influence of Regularization via Multiobjective Bilevel Optimizationcited by 3

50 most cited of 88 All 88 (JSON)