Recommender systems have become an integral part of online services due to their ability to
help users locate specific information in a sea of data. However, existing studies show that …

With the widespread use of Internet of things (IoT), mobile phones, connected devices and
artificial intelligence (AI), recommender systems (RSs) have become a booming technology …

Recent years have seen a proliferation of research on adversarial machine learning.
Numerous papers demonstrate powerful algorithmic attacks against a wide variety of …

Natural language processing (NLP) systems have been proven to be vulnerable to backdoor
attacks, whereby hidden features (backdoors) are trained into a language model and may …

We investigate whether model extraction can be used to 'steal'the weights of sequential
recommender systems, and the potential threats posed to victims of such attacks. This type …

Federated Recommender Systems (FedRecs) are considered privacy-preserving
techniques to collaboratively learn a recommendation model without sharing user data …

Data poisoning attacks and backdoor attacks aim to corrupt a machine learning classifier via
modifying, adding, and/or removing some carefully selected training examples, such that the …

Federated Recommendation (FR) has received con-siderable popularity and attention in the
past few years. In FR, for each user, its feature vector and interaction data are kept locally on …

Recent studies have shown that recommender systems are vulnerable, and it is easy for
attackers to inject well-designed malicious profiles into the system, resulting in biased …

Recent studies have shown that deep neural networks-based recommender systems are
vulnerable to adversarial attacks, where attackers can inject carefully crafted fake user …