Adversarial Regression with Multiple Learners

06/06/2018
by   Liang Tong, et al.
0

Despite the considerable success enjoyed by machine learning techniques in practice, numerous studies demonstrated that many approaches are vulnerable to attacks. An important class of such attacks involves adversaries changing features at test time to cause incorrect predictions. Previous investigations of this problem pit a single learner against an adversary. However, in many situations an adversary's decision is aimed at a collection of learners, rather than specifically targeted at each independently. We study the problem of adversarial linear regression with multiple learners. We approximate the resulting game by exhibiting an upper bound on learner loss functions, and show that the resulting game has a unique symmetric equilibrium. We present an algorithm for computing this equilibrium, and show through extensive experiments that equilibrium models are significantly more robust than conventional regularized linear regression.

READ FULL TEXT

page 14

page 17

research
06/06/2019

Robust Attacks against Multiple Classifiers

We address the challenge of designing optimal adversarial noise algorith...
research
05/18/2023

Attacks on Online Learners: a Teacher-Student Analysis

Machine learning models are famously vulnerable to adversarial attacks: ...
research
04/30/2021

Automatic Debiased Machine Learning via Neural Nets for Generalized Linear Regression

We give debiased machine learners of parameters of interest that depend ...
research
04/06/2023

Reliable Learning for Test-time Attacks and Distribution Shift

Machine learning algorithms are often used in environments which are not...
research
10/12/2017

Game-Theoretic Design of Secure and Resilient Distributed Support Vector Machines with Adversaries

With a large number of sensors and control units in networked systems, d...
research
11/20/2022

Adversarial Cheap Talk

Adversarial attacks in reinforcement learning (RL) often assume highly-p...
research
05/17/2019

Merging versus Ensembling in Multi-Study Machine Learning: Theoretical Insight from Random Effects

A critical decision point when training predictors using multiple studie...

Please sign up or login with your details

Forgot password? Click here to reset