sisinflab/adversarial-recommender-systems-survey
📄 Papersisinflab
A comprehensive literature review on adversarial machine learning in recommender systems and GAN-based generative applications.
The sisinflab/adversarial-recommender-systems-survey is a structured academic resource that synthesizes the state-of-the-art in adversarial machine learning as applied to recommender systems (RS). The survey is divided into two critical pillars: first, it examines the security landscape, detailing various adversarial attack vectors against RS and the corresponding defense mechanisms designed to harden these models. Second, it explores the utility of GANs in generative tasks, highlighting how adversarial training can be harnessed to learn high-dimensional data distributions and improve recommendation quality. By reviewing 74 seminal papers from top-tier AI and RS conferences, this repository offers a systematic taxonomy of the field. It is an essential resource for developers and researchers looking to build more robust recommendation engines or explore the generative potential of adversarial training in personalized systems.
💡Highlights
- ├─74-paper comprehensive review
- ├─Covers RS security & GANs
- └─Taxonomy of AML in RecSys
🎯For
- ├─AI Researchers
- └─Security Engineers