Browsing by Subject "recommender systems"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Assessing the Value of Transparency in Recommender Systems: An End-User Perspective
    (ACM, 2018-10) Vorm, Eric S.; Miller, Andrew D.; Human-Centered Computing, School of Informatics and Computing
    Recommender systems, especially those built on machine learning, are increasing in popularity, as well as complexity and scope. Systems that cannot explain their reasoning to end-users risk losing trust with users and failing to achieve acceptance. Users demand interfaces that afford them insights into internal workings, allowing them to build appropriate mental models and calibrated trust. Building interfaces that provide this level of transparency, however, is a significant design challenge, with many design features that compete, and little empirical research to guide implementation. We investigated how end-users of recommender systems value different categories of information to help in determining what to do with computer-generated recommendations in contexts involving high risk to themselves or others. Findings will inform future design of decision support in high-criticality contexts.
  • Thumbnail Image
    Item
    Multi-Armed-Bandit-based Shilling Attack on Collaborative Filtering Recommender Systems
    (IEEE, 2020-12) Palanisamy Sundar, Agnideven; Li, Feng; Zou, Xukai; Hu, Qin; Gao, Tianchong; Computer and Information Science, School of Science
    Collaborative Filtering (CF) is a popular recommendation system that makes recommendations based on similar users' preferences. Though it is widely used, CF is prone to Shilling/Profile Injection attacks, where fake profiles are injected into the CF system to alter its outcome. Most of the existing shilling attacks do not work on online systems and cannot be efficiently implemented in real-world applications. In this paper, we introduce an efficient Multi-Armed-Bandit-based reinforcement learning method to practically execute online shilling attacks. Our method works by reducing the uncertainty associated with the item selection process and finds the most optimal items to enhance attack reach. Such practical online attacks open new avenues for research in building more robust recommender systems. We treat the recommender system as a black box, making our method effective irrespective of the type of CF used. Finally, we also experimentally test our approach against popular state-of-the-art shilling attacks.