Related papers: Model Stealing Attack against Recommender System
Model extraction attacks aim to replicate the functionality of a black-box model through query access, threatening the intellectual property (IP) of machine-learning-as-a-service (MLaaS) providers. Defending against such attacks is…
Gradient leakage has been identified as a potential source of privacy breaches in modern image processing systems, where the adversary can completely reconstruct the training images from leaked gradients. However, existing methods are…
Effective methodologies for evaluating recommender systems are critical, so that such systems can be compared in a sound manner. A commonly overlooked aspect of recommender system evaluation is the selection of the data splitting strategy.…
Learning reward models from pairwise comparisons is a fundamental component in a number of domains, including autonomous control, conversational agents, and recommendation systems, as part of a broad goal of aligning automated decisions…
Federated learning has recently been applied to recommendation systems to protect user privacy. In federated learning settings, recommendation systems can train recommendation models only collecting the intermediate parameters instead of…
Deep reinforcement learning policies, which are integral to modern control systems, represent valuable intellectual property. The development of these policies demands considerable resources, such as domain expertise, simulation fidelity,…
With the rapid growth of information, recommender systems have become integral for providing personalized suggestions and overcoming information overload. However, their practical deployment often encounters ``dirty'' data, where noise or…
Models can expose sensitive information about their training data. In an attribute inference attack, an adversary has partial knowledge of some training records and access to a model trained on those records, and infers the unknown values…
With the growing privacy concerns in recommender systems, recommendation unlearning, i.e., forgetting the impact of specific learned targets, is getting increasing attention. Existing studies predominantly use training data, i.e., model…
The use of relevant metrics of software systems could improve various software engineering tasks, but identifying relationships among metrics is not simple and can be very time consuming. Recommender systems can help with this…
This work addresses the challenges related to attacks on collaborative tagging systems, which often comes in a form of malicious annotations or profile injection attacks. In particular, we study various countermeasures against two types of…
Can machine learning models for recommendation be easily fooled? While the question has been answered for hand-engineered fake user profiles, it has not been explored for machine learned adversarial attacks. This paper attempts to close…
Recommendation systems and content filtering approaches based on annotations and ratings, essentially rely on users expressing their preferences and interests through their actions, in order to provide personalised content. This activity,…
Machine learning models can leak information regarding the dataset they have trained. In this paper, we present the first membership inference attack against black-boxed object detection models that determines whether the given data records…
With an increase in low-cost machine learning APIs, advanced machine learning models may be trained on private datasets and monetized by providing them as a service. However, privacy researchers have demonstrated that these models may leak…
Recent approaches in machine learning often solve a task using a composition of multiple models or agentic architectures. When targeting a composed system with adversarial attacks, it might not be computationally or informationally feasible…
Pattern recognition and machine learning techniques have been increasingly adopted in adversarial settings such as spam, intrusion and malware detection, although their security against well-crafted attacks that aim to evade detection by…
Deep neural networks are normally executed in the forward direction. However, in this work, we identify a vulnerability that enables models to be trained in both directions and on different tasks. Adversaries can exploit this capability to…
Machine learning (ML) has been widely adopted in various privacy-critical applications, e.g., face recognition and medical image analysis. However, recent research has shown that ML models are vulnerable to attacks against their training…
Data-free model stealing involves replicating the functionality of a target model into a substitute model without accessing the target model's structure, parameters, or training data. The adversary can only access the target model's…