logo_tutorial uqcqu_logo uq_logo


Welcome! This is the page of our tutorial “Towards Secure and Robust Recommender Systems: Recent Advances and Future Prospectives” at The 18th ACM International Conference on Web Search and Data Mining (WSDM).

(Last update: 23/09/2024)

Time

CET 14:00 - 15:30, 10/03/2025

Description

As recommender systems (RS) continue to evolve, the field has seen a pivotal shift from model-centric to data-centric paradigms, where the quality, integrity, and security of data are increasingly becoming the key drivers of system performance and personalization. This transformation has unlocked new avenues for more precise and tailored recommendations, yet it also introduces significant challenges. As reliance on data intensifies, RS face mounting threats that can compromise both their effectiveness and user trust. These challenges include (1) Malicious Data Manipulation, where adversaries corrupt or tamper with datasets, distorting recommendation outcomes and undermining system reliability; (2) Data Privacy Leakage, where adversarial actors exploit system outputs to infer sensitive user information, leading to serious privacy concerns; and (3) Erroneous Data Noise, where inaccuracies, inconsistencies, and redundant data obscure the true user preferences, degrading recommendation quality and user satisfaction. By focusing on these critical data-centric challenges, this tutorial aims to equip participants with the knowledge to build RS that are secure, privacy-preserving, and resilient to data-driven threats, ensuring reliable and trustworthy performance in real-world environments. In addition, attendees will gain hands-on experience with our newly released toolkit for RS-based attacks and defenses, providing them with practical, actionable insights into safeguarding RS against emerging vulnerabilities.

Presenters

Hongzhi Yin is an ARC Future Fellow, Full Professor, and the Director of the Responsible Big Data Intelligence Lab at The University of Queensland. He has published 300+ papers with an H-index of 77, making notable contributions to recommender systems, graph learning, decentralized learning, and edge intelligence. He has rich lecture experience and taught five relevant courses, such as information retrieval and web search, social media analytics, and responsible data science. Additionally, he has delivered 20+ keynotes and tutorials at the top-tier conferences like WWW’17,22,24, DASFAA’23, and KDD’17.

Zongwei Wang is currently pursuing his Ph.D. at Chongqing University and is a visiting student at The University of Queensland. His research work has been published on top data mining conferences such as KDD, TIST, PAKDD, WSDM, etc. He has ample experience tutoring relevant courses and has presented his work at multiple top-tier conferences, such as KDD and PAKDD.

Junliang Yu is an ARC DECRA Fellow at the University of Queensland. His research interests include recommender systems, data-centric AI, and graph learning. With over 30 publications in premier venues, he is a recognized contributor in his field. He has delivered multiple lectures at summer schools and taught courses on recommender systems and social media analytics. He organized two well-received tutorials on self-supervised recommender systems at WWW’22 and DASFAA’23 and presented his work at multiple top-tier conferences.

Tong Chen is a Senior Lecturer and ARC DECRA Fellow at The University of Queensland. His research on lightweight, on-device, and trustworthy recommender systems has been published in top-tier international venues such as KDD, SIGIR, WWW, TKDE, WSDM, TNNLS, TOIS, and CIKM. He has ample track records in lecturing, evidenced by his course design and delivery experience in business analytics, teaching experience in data science, and invited tutorials on cutting-edge recommender systems at the WWW’22, 24, and DASFAA’23.

Shazia Sadiq is a Full Professor at The University of Queensland. Her research focuses on responsible data management and aims to reduce the socio-technical barriers to data-driven transformation. She is a Fellow of the Australian Academy of Technological Sciences and Engineering. Throughout her 25-year career, she has received numerous invitations to speak at prestigious conferences, academic institutions, and industry forums, delivering over 20 tutorials, talks, panels, and keynotes. One notable example is the Keynote talk at SIGMOD’23.

Min Gao works as a Full Professor at Chongqing University, China. She has published 100+ papers, making notable contributions to recommender systems and data mining. She has been SPC or PC for many top conferences, such as WWW, IJCAI, AAAI, KDD, WSDM, and CIKM. Prof. Min Gao has rich lecture experience and has taught three relevant courses, such as advanced machine learning, computer networks, and advanced database, and has presented her work at multiple top-tier conferences.

Outline

The tutorial is delivered as a lecture-style tutorial (3 hours in duration) that includes:

Targeted Audience

This tutorial is designed for a broad audience, including academic and industrial researchers, graduate students, and practitioners from the recommendation field and related areas. By the end of the tutorial, participants will have a solid understanding of basic poisoning attacks and defensive strategies to enhance the robustness and security of recommendation systems. Additionally, they will gain hands-on experience using an open-source toolkit. While prior knowledge of recommendation systems is preferred, the tutorial will also cover foundational concepts to ensure better engagement and accessibility for all attendees.

Our papers on secure and robust recommendation