A Black-Box Attack Model for Visually-Aware Recommender Systems
Due to the advances in deep learning, visually-aware recommender systems (RS) have recently attracted increased research interest. Such systems combine collaborative signals with images, usually represented as feature vectors outputted by pre-trained image models. Since item catalogs can be huge, recommendation service providers often rely on images that are supplied by the item providers. In this work, we show that relying on such external sources can make an RS vulnerable to attacks, where the goal of the attacker is to unfairly promote certain pushed items. Specifically, we demonstrate how a new visual attack model can effectively influence the item scores and rankings in a black-box approach, i.e., without knowing the parameters of the model. The main underlying idea is to systematically create small human-imperceptible perturbations of the pushed item image and to devise appropriate gradient approximation methods to incrementally raise the pushed item's score. Experimental evaluations on two datasets show that the novel attack model is effective even when the contribution of the visual features to the overall performance of the recommender system is modest.
Code (0)
등록된 구현이 없습니다.
Tasks
Recommendation SystemsSimilar Papers 제목 키워드 기반
Adversarial Item Promotion on Visually-Aware Recommender Systems by Guided Diffusion
Visually-aware recommender systems have found widespread application in domains where visual elements significantly contribute to the inference of users' potential preferences. While the incorporation of visual informati…
Recommendation SystemsManipulating Visually-aware Federated Recommender Systems and Its Countermeasures
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 SystemsBlack-Box Attacks on Sequential Recommenders via Data-Free Model Extraction
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 of risk has attracted attention in image…
Data PoisoningKnowledge DistillationModel extractionRecommendation Systems+4Adversarial Item Promotion: Vulnerabilities at the Core of Top-N Recommenders that Use Images to Address Cold Start
E-commerce platforms provide their customers with ranked lists of recommended items matching the customers' preferences. Merchants on e-commerce platforms would like their items to appear as high as possible in the top-N…
Recommendation SystemsMulti-agent Attacks for Black-box Social Recommendations
The rise of online social networks has facilitated the evolution of social recommender systems, which incorporate social relations to enhance users' decision-making process. With the great success of Graph Neural Network…
Decision MakingMulti-agent Reinforcement LearningRecommendation Systems