paper-with-me

Papers

Data Poisoning Attacks on Factorization-Based Collaborative Filtering

2016-08-29 · NeurIPS 2016 12 · Bo Li, Yining Wang, Aarti Singh, Yevgeniy Vorobeychik

Recommendation and collaborative filtering systems are important in modern information and e-commerce applications. As these systems are becoming increasingly popular in the industry, their outputs could affect business decision making, introducing incentives for an adversarial party to compromise the availability or integrity of such systems. We introduce a data poisoning attack on collaborative filtering systems. We demonstrate how a powerful attacker with full knowledge of the learner can generate malicious data so as to maximize his/her malicious objectives, while at the same time mimicking normal user behavior to avoid being detected. While the complete knowledge assumption seems extreme, it enables a robust assessment of the vulnerability of collaborative filtering schemes to highly motivated attacks. We present efficient solutions for two popular factorization-based collaborative filtering algorithms: the \emph{alternative minimization} formulation and the \emph{nuclear norm minimization} method. Finally, we test the effectiveness of our proposed algorithms on real-world data and discuss potential defensive strategies.

📄 PDF Abstract BibTeX arXiv:1608.08182

Code (0)

등록된 구현이 없습니다.

Tasks

Collaborative FilteringData PoisoningDecision Making

Similar Papers 제목 키워드 기반

Data Poisoning Attacks on Neighborhood-based Recommender Systems

2019-12-01 · Liang Chen, Yangjun Xu, Fenfang Xie, Min Huang 외

Nowadays, collaborative filtering recommender systems have been widely deployed in many commercial companies to make profit. Neighbourhood-based collaborative filtering is common and effective. To date, despite its effec…

Collaborative FilteringData PoisoningRecommendation Systems

Manipulating Visually-aware Federated Recommender Systems and Its Countermeasures

2023-05-14 · Wei Yuan, Shilong Yuan, Chaoqun Yang, Quoc Viet Hung Nguyen 외

Federated recommender systems (FedRecs) have been widely explored recently due to their ability to protect user data privacy. In FedRecs, a central server collaboratively learns recommendation models by sharing model pub…

Collaborative FilteringModel PoisoningPrivacy PreservingRecommendation Systems

Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation

2024-10-30 · Kaike Zhang, Qi Cao, Yunfan Wu, Fei Sun 외

Adversarial Collaborative Filtering (ACF), which typically applies adversarial perturbations at user and item embeddings through adversarial training, is widely recognized as an effective strategy for enhancing the robus…

Collaborative FilteringRecommendation Systems

Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering

2021-09-13 · Jian Xu, Shao-Lun Huang, Linqi Song, Tian Lan

Gradient-based training in federated learning is known to be vulnerable to faulty/malicious clients, which are often modeled as Byzantine clients. To this end, previous work either makes use of auxiliary data at paramete…

Federated LearningModel Poisoningtext-classificationText Classification

Sentinel: An Aggregation Function to Secure Decentralized Federated Learning

2023-10-12 · Chao Feng, Alberto Huertas Celdrán, Janosch Baltensperger, Enrique Tomás Martínez Beltrán 외

Decentralized Federated Learning (DFL) emerges as an innovative paradigm to train collaborative models, addressing the single point of failure limitation. However, the security and trustworthiness of FL and DFL are compr…

Federated LearningManagement