Minghong Fang

Influence Function based Data Poisoning Attacks to Top-N Recommender Systems

2020

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 …

Periodic Recovery From Poisoning Attacks in Machine Learning

2025 · IEEE Transactions on Dependable and Secure Computing

Recovery from poisoning attacks aims to eliminate the influence of a given set of deleted poisoned training data on a model. In practice, model recovery often happensperiodicallysince data deletion occurs repeatedly after a model has …

Traceback of Poisoning Attacks to Retrieval-Augmented Generation

2025 · arXiv (Cornell University)

Large language models (LLMs) integrated with retrieval-augmented generation (RAG) systems improve accuracy by leveraging external knowledge sources. However, recent research has revealed RAG's susceptibility to poisoning attacks, where the attacker injects poisoned texts into the …

Poisoning Attacks to Graph-Based Recommender Systems

2018

Recommender system is an important component of many web services to help users locate items that match their interests. Several studies showed that recommender systems are vulnerable to poisoning attacks, in which an attacker injects …