Robust Linear Regression Against Training Data Poisoning

By Chang Liu, Bo Li, Yevgeniy Vorobeychik, Alina Oprea. 2017

99 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Mechanics, Optimization & Training, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Mechanics

In Optimization & Training

In Safety, Robustness & Interpretability

Citations in the corpus

Local Model Poisoning Attacks to Byzantine-Robust Federated Learning (2019, background): “Another category of defenses [20, 30, 35, 55] proposed new loss functions, optimizing which obtains model parameters and detects the injected malicious data simultaneously.”
Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning (2017, background): “Poisoning attacks can be thus regarded as outliers , and countered using data sanitization (i.e., attack detection and removal) [94, 97, 99], and robust learning (i.e., learning algorithms based on robust statistics that are intrinsically less sensitive to outlying training samples) [23, 98].”
Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks (2018, methodology): “Some defenses against data poisoning attacks have also been proposed: for example, Liu et al. [26] discuss a technique for performing robust linear regression in the presence of noisy data and adversarially poisoned training samples by recovering a low-rank subspace of the feature matrix.”
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning (2017, methodology): “Such statistical robust learning algorithms have been proposed for several traditional machine learning models such as linear and logistic regressions [14], [18], [27], [16], [39], [61].”
Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning (2018, methodology): “In adversarial settings, robust methods for dealing with arbitrary corruptions of data have been proposed in the context of linear regression [12], high-dimensional sparse regression [11], logistic regression [17], and linear regression with low rank feature matrix [34].”
A Comprehensive Survey on Poisoning Attacks and Countermeasures in Machine Learning (2022, methodology): “…Multiple Kernel Learning model-driven LM UnT 2012 [88] cross-models model-driven LM UnT 2013 [104] cross-models model-driven cross-attacks UnT 2020 [70] linear regression both classes DM UnT 2017 UnT: Untargeted poisoning attack, LM: label manipulation, DM: data manipulation, cross-models: protect…”
Attacks on Machine Learning: Lurking Danger for Accountability (2019, methodology): “Attack [4] Linear Regression Supervised Yes/No Poisoning Attack [8, 35, 41] No Model Inversion [27] Lowd-Meek Attack [44, 72] Logistic Regression Supervised No Equation-solving Attack [49] Hyperparameter Stealing [73] Adversarial Examples [52, 70, 71] Multi-class Logistic Regression Supervised No Eq”
Data Poisoning Attacks Against Federated Learning Systems (2020, methodology): “Several poisoning attacks were developed for popular ML models including SVM [6,12,44,45,50,52], regression [19], dimensionality reduction [51], linear classiﬁers [12,23,57], unsupervised learning [7], and more recently, neural networks [12,30,42,45,53,58].”
A Backdoor Attack Against LSTM-Based Text Classification Systems (2019, background): “Similar poisoning strategies which target other traditional machine learning models have also been developed, such as regression models [17] and clustering models [18].”
TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems (2019, background): “…in this category mainly focus on three kinds of methods – (1) eliminating contaminated training data and retraining learning models ( e.g., [5, 27, 41]); (2) trimming malicious neurons and re-calibrating the corresponding network ( e.g., [28]) as well as (3) restoring a trigger from an…”