Countermeasures for Regression Learning Against Poisoning Attacks
Explore the impact of poisoning attacks on regression learning and discover effective countermeasures. Learn about adversarial models, attacking methods, defenses, and evaluations in machine learning security.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning Matthew Jagielski, Alina Oprea, Battista Biggio, Chang Liu, Cristina Nita- Rotaru, and Bo Li Northeastern University, Boston; MA University of Cagliari, Italy; Pluribus One, Italy; UC Berkeley, Berkeley, CA 2018 Oakland
Background Poison Attack Inject few corrupted points in training set Categories: Availability Attack Backdoor Realistic Significance Example Spam Filters Sentiment Analysis
Highlight FIRST to consider poisoning linear regression under different adversarial models Propose an adversarial framework (OptP) Design a fast statistic attack (StaP) Present a defense method (TRIM)
Adversary Goal: Poisoning Availability Knowledge White-box: Know everything Black-box: Don t Know and ???(But have ??? Capability Inject before model is trained Strategy )
Initialize Before Attack Projection to x, y to [0, 1] Setting ?? to: 1- ?? Round ??
Attacking Methods Optimize Attack (OptP) Statistic Attack (StaP) Sample from multivariate normal distribution with training set s mean and covariance Only need black-box
