Related papers: Poisoning Attacks against Recommender Systems: A S…
As machine learning becomes widely used for automated decisions, attackers have strong incentives to manipulate the results and models generated by machine learning algorithms. In this paper, we perform the first systematic study of…
Property inference attacks consider an adversary who has access to the trained model and tries to extract some global statistics of the training data. In this work, we study property inference in scenarios where the adversary can…
This paper demonstrates a fatal vulnerability in natural language inference (NLI) and text classification systems. More concretely, we present a 'backdoor poisoning' attack on NLP models. Our poisoning attack utilizes conditional…
Recommender systems are an essential part of any e-commerce platform. Recommendations are typically generated by aggregating large amounts of user data. A malicious actor may be motivated to sway the output of such recommender systems by…
Retrieval-augmented generation (RAG) systems can effectively mitigate the hallucination problem of large language models (LLMs),but they also possess inherent vulnerabilities. Identifying these weaknesses before the large-scale real-world…
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…
Presently, with the assistance of advanced LLM application development frameworks, more and more LLM-powered applications can effortlessly augment the LLMs' knowledge with external content using the retrieval augmented generation (RAG)…
Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models'…
Machine learning has become an important component for many systems and applications including computer vision, spam filtering, malware and network intrusion detection, among others. Despite the capabilities of machine learning algorithms…
Using 286 research papers collected from Web of Science, ScienceDirect, SpringerLink, arXiv, and Google Scholar databases, a systematic review methodology was adopted to review and summarize the current challenges and potential future…
Machine learning systems are deployed in critical settings, but they might fail in unexpected ways, impacting the accuracy of their predictions. Poisoning attacks against machine learning induce adversarial modification of data used by a…
We consider availability data poisoning attacks, where an adversary aims to degrade the overall test accuracy of a machine learning model by crafting small perturbations to its training data. Existing poisoning strategies can achieve the…
Recent research has successfully demonstrated new types of data poisoning attacks. To address this problem, some researchers have proposed both offline and online data poisoning detection defenses which employ machine learning algorithms to…
Recently, NLP has seen a surge in the usage of large pre-trained models. Users download weights of models pre-trained on large datasets, then fine-tune the weights on a task of their choice. This raises the question of whether downloading…
With the widespread availability of pretrained Large Language Models (LLMs) and their training datasets, concerns about the security risks associated with their usage has increased significantly. One of these security risks is the threat of…
Recent studies have demonstrated the vulnerability of recommender systems to data privacy attacks. However, research on the threat to model privacy in recommender systems, such as model stealing attacks, is still in its infancy. Some…
Data poisoning is a training-time attack that undermines the trustworthiness of learned models. In a targeted data poisoning attack, an adversary manipulates the training dataset to alter the classification of a targeted test point. Given…
Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS). However, while these systems have flourished, their susceptibility to security threats has been largely…
Recently, recommender systems have achieved promising performances and become one of the most widely used web applications. However, recommender systems are often trained on highly sensitive user data, thus potential data leakage from…
With the rise of third parties in the machine learning pipeline, the service provider in "Machine Learning as a Service" (MLaaS), or external data contributors in online learning, or the retraining of existing models, the need to ensure the…