相关论文: Precision Profile Pollution Attack on Sequential R…

Sequential Recommenders, which exploit dynamic user intents through interaction sequences, is vulnerable to adversarial attacks. While existing attacks primarily rely on data poisoning, they require large-scale user access or fake profiles…

While sequential recommender systems achieve significant improvements on capturing user dynamics, we argue that sequential recommenders are vulnerable against substitution-based profile pollution attacks. To demonstrate our hypothesis, we…

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…

Instruction fine-tuning attacks pose a serious threat to large language models (LLMs) by subtly embedding poisoned examples in fine-tuning datasets, leading to harmful or unintended behaviors in downstream applications. Detecting such…

Addressing data integrity challenges, such as unlearning the effects of data poisoning after model training, is necessary for the reliable deployment of machine learning models. State-of-the-art influence functions, such as EK-FAC and TRAK,…

Federated Recommendation (FR) has received considerable popularity and attention in the past few years. In FR, for each user, its feature vector and interaction data are kept locally on its own client thus are private to others. Without the…

Federated recommender systems (FedRec) have emerged as a promising approach to provide personalized recommendations while protecting user privacy. However, recent studies have shown their vulnerability to poisoning attacks, where malicious…

Recommender systems play a central role in digital platforms by providing personalized content. They often use methods such as collaborative filtering and machine learning to accurately predict user preferences. Although these systems offer…

Considering the premise that the number of products offered grow in an exponential fashion and the amount of data that a user can assimilate before making a decision is relatively small, recommender systems help in categorizing content…

Influence functions are commonly used to attribute model behavior to training documents. We explore the reverse: crafting training data that induces model behavior. Our framework, Infusion, uses scalable influence-function approximations to…

Recommender systems play a crucial role in helping users to find their interested information in various web services such as Amazon, YouTube, and Google News. Various recommender systems, ranging from neighborhood-based,…

Recommender system usually faces popularity bias issues: from the data perspective, items exhibit uneven (long-tail) distribution on the interaction frequency; from the method perspective, collaborative filtering methods are prone to…

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 fake…

Due to the growing privacy concerns, decentralization emerges rapidly in personalized services, especially recommendation. Also, recent studies have shown that centralized models are vulnerable to poisoning attacks, compromising their…

Federated learning (FL) is a feasible technique to learn personalized recommendation models from decentralized user data. Unfortunately, federated recommender systems are vulnerable to poisoning attacks by malicious clients. Existing…

Recently, influence functions present an apparatus for achieving explainability for deep neural models by quantifying the perturbation of individual train instances that might impact a test prediction. Our objectives in this paper are…

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 effectiveness, there has…

Precise user and item embedding learning is the key to building a successful recommender system. Traditionally, Collaborative Filtering(CF) provides a way to learn user and item embeddings from the user-item interaction history. However,…

Targeted training-set attacks inject malicious instances into the training set to cause a trained model to mislabel one or more specific test instances. This work proposes the task of target identification, which determines whether a…

Among the most critical limitations of deep learning NLP models are their lack of interpretability, and their reliance on spurious correlations. Prior work proposed various approaches to interpreting the black-box models to unveil the…