Securing Recommender Systems

May 13, 2023

This research focuses on protecting open systems that use user input (ratings, comments, reviews, etc.) as a means of producing recommendations and how these systems that are based on subjective measures can be protected against malicious attacks designed to manipulate the recommender system output.

Cybersecurity Machine Learning
Chad Williams
Authors
Chad Williams
Associate Professor
Chair, Department of Computer Science
My research interests include software engineering, intrusion detection, machine learning, and teaching methodology.

Publications

Defending recommender systems: detection of profile injection attacks
Chad Williams, Bamshad Mobasher, Robin Burke
PDF Cite Project
Detecting profile injection attacks in collaborative filtering: a classification-based approach
Chad Williams, Bamshad Mobasher, Robin Burke, Runa Bhaumik
PDF Cite Project
Toward trustworthy recommender systems: An analysis of attack models and algorithm robustness
B. Mobasher, R. Burke, R. Bhaumik, Chad Williams
PDF Cite Project
Evaluation of profile injection attacks in collaborative recommender systems
Chad Williams, Runa Bhaumik, JJ Sandvig, Bamshad Mobasher, Robin Burke
PDF Cite Project
Analysis and detection of segment-focused attacks against collaborative recommendation
Bamshad Mobasher, Robin Burke, Chad Williams, Runa Bhaumik
PDF Cite Project
Analysis and detection of segment-focused attacks against collaborative recommendation
B. Mobasher, R. Burke, Chad Williams, R. Bhaumik
PDF Cite Project
Classification features for attack detection in collaborative recommender systems
Robin Burke, Bamshad Mobasher, Chad Williams, Runa Bhaumik
PDF Cite Project
Detecting profile injection attacks in collaborative recommender systems
*Winner of Best Paper Award
Robin Burke, Bamshad Mobasher, Chad Williams, Runa Bhaumik
PDF Cite Project
Detection of obfuscated attacks in collaborative recommender systems
Chad Williams, Bamshad Mobasher, Robin Burke, Jeff Sandvig, Runa Bhaumik
PDF Cite Project
Profile injection attack detection for securing collaborative recommender systems
Advisors: Bamshad Mobasher
Chad Williams
PDF Cite Project
Securing collaborative filtering against malicious attacks through anomaly detection
Runa Bhaumik, Chad Williams, Bamshad Mobasher, Robin Burke
PDF Cite Project
The impact of attack profile classification on the robustness of collaborative recommendation
Chad Williams, Runa Bhaumik, Robin Burke, Bamshad Mobasher
PDF Cite Project
Collaborative recommendation vulnerability to focused bias injection attacks
Robin Burke, Bamshad Mobasher, Runa Bhaumik, Chad Williams
PDF Cite Project
Effective attack models for shilling item-based collaborative filtering systems
Bamshad Mobasher, Robin Burke, Runa Bhaumik, Chad Williams
PDF Cite Project
Segment-based injection attacks against collaborative filtering recommender systems
Robin Burke, Bamshad Mobasher, Runa Bhaumik, Chad Williams
PDF Cite Project