Targeted Poisoning Attacks on Social Recommender Systems
Targeted Poisoning Attacks on Social Recommender Systems
复制标题
DOI：
10.1109/globecom38437.2019.9013539
复制
发表时间：
2019-12
期刊：
影响因子：
--
通讯作者：
Rui Hu;Yuanxiong Guo;M. Pan;Yanmin Gong
中科院分区：
文献类型：
--
作者：
Rui Hu;Yuanxiong Guo;M. Pan;Yanmin Gong
随着在线社交网络的普及，依靠个人的社交关系来进行个性化推荐的社交推荐已经成为可能。这为敌对方引入了漏洞，以通过利用他们的社交关系来损害对用户的推荐。在本文中，我们提出了有针对性的中毒攻击的因子分解为基础的社会推荐系统中，攻击者的目的是促进一个项目的一组目标用户通过注入虚假的评级和社会联系。我们将最优投毒攻击表示为一个双层规划，并给出了一个求解最优投毒攻击策略的有效算法。然后，我们在真实世界的数据集上评估了所提出的攻击策略，并证明了社会推荐系统对有针对性的中毒攻击是敏感的。我们发现，用户在社会推荐系统可以攻击，即使他们没有直接的社会联系与攻击者。
With the popularity of online social networks, social recommendations that rely on one’s social connections to make personalized recommendations have become possible. This introduces vulnerabilities for an adversarial party to compromise the recommendations for users by utilizing their social connections. In this paper, we propose the targeted poisoning attack on the factorization-based social recommender system in which the attacker aims to promote an item to a group of target users by injecting fake ratings and social connections. We formulate the optimal poisoning attack as a bi-level program and develop an efficient algorithm to find the optimal attacking strategy. We then evaluate the proposed attacking strategy on real-world dataset and demonstrate that the social recommender system is sensitive to the targeted poisoning attack. We find that users in the social recommender system can be attacked even if they do not have direct social connections with the attacker.