Influence Function based Data Poisoning Attacks to Top-N Recommender Systems
Influence Function based Data Poisoning Attacks to Top-N Recommender Systems
复制标题
DOI：
10.1145/3366423.3380072
复制
发表时间：
2020-02
期刊：
影响因子：
--
通讯作者：
Minghong Fang;N. Gong;Jia Liu
中科院分区：
文献类型：
--
作者：
Minghong Fang;N. Gong;Jia Liu
推荐系统是网络服务吸引用户的重要组成部分。流行的推荐系统使用大量众包的用户-项目交互数据（例如评分）来建模用户偏好和项目属性；然后将与用户偏好最匹配的前 N 个项目推荐给用户。在这项工作中，我们表明攻击者可以向推荐系统发起数据中毒攻击，通过向假用户注入精心设计的用户-项目交互数据来根据攻击者的意愿提出推荐。具体来说，攻击者可以欺骗推荐系统向尽可能多的普通用户推荐目标项目。我们专注于基于矩阵分解的推荐系统，因为它们已在行业中广泛部署。考虑到攻击者可以注入的假用户数量，我们将假用户评分的制定作为一个优化问题。然而，这个优化问题很难解决，因为它是一个非凸整数规划问题。为了应对这一挑战，我们开发了几种技术来近似解决优化问题。例如，我们利用影响函数来选择对推荐有影响力的普通用户的子集，并根据这些有影响力的用户来解决我们制定的优化问题。我们的结果表明我们的攻击是有效的并且优于现有方法。
Recommender system is an essential component of web services to engage users. Popular recommender systems model user preferences and item properties using a large amount of crowdsourced user-item interaction data, e.g., rating scores; then top-N items that match the best with a user’s preference are recommended to the user. In this work, we show that an attacker can launch a data poisoning attack to a recommender system to make recommendations as the attacker desires via injecting fake users with carefully crafted user-item interaction data. Specifically, an attacker can trick a recommender system to recommend a target item to as many normal users as possible. We focus on matrix factorization based recommender systems because they have been widely deployed in industry. Given the number of fake users the attacker can inject, we formulate the crafting of rating scores for the fake users as an optimization problem. However, this optimization problem is challenging to solve as it is a non-convex integer programming problem. To address the challenge, we develop several techniques to approximately solve the optimization problem. For instance, we leverage influence function to select a subset of normal users who are influential to the recommendations and solve our formulated optimization problem based on these influential users. Our results show that our attacks are effective and outperform existing methods.