Stealthy LLM-Driven Data Poisoning Attacks Against Embedding-Based Retrieval-Augmented Recommender Systems
We present a systematic study of provider-side data poisoning in retrieval-augmented recommender systems (RAG-based). By modifying only a small fraction of tokens within item descriptions -- for instance, adding emotional keywords or borrowing phrases from semantically related items -- an attacker can significantly promote or demote targeted items. We formalize these attacks under token-edit and semantic-similarity constraints, and we examine their effectiveness in both promotion (long-tail items) and demotion (short-head items) scenarios. Our experiments on MovieLens, using two large language model (LLM) retrieval modules, show that even subtle attacks shift final rankings and item exposures while eluding naive detection. The results underscore the vulnerability of RAG-based pipelines to small-scale metadata rewrites and emphasize the need for robust textual consistency checks and provenance tracking to thwart stealthy provider-side poisoning.
Code (0)
등록된 구현이 없습니다.
Tasks
Data PoisoningLanguage ModelingLanguage ModellingLarge Language ModelRAGRecommendation SystemsRetrievalSemantic SimilaritySemantic Textual SimilaritySimilar Papers 제목 키워드 기반
Stealthy Poisoning Attacks Bypass Defenses in Regression Settings
Regression models are widely used in industrial processes, engineering, and in natural and physical sciences, yet their robustness to poisoning has received less attention. When it has, studies often assume unrealistic t…
Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits
Adversarial attacks against stochastic multi-armed bandit (MAB) algorithms have been extensively studied in the literature. In this work, we focus on reward poisoning attacks and find most existing attacks can be easily …
Multi-Armed BanditsSubpopulation Data Poisoning Attacks
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 …
BIG-bench Machine LearningData PoisoningAnalysis and Detectability of Offline Data Poisoning Attacks on Linear Dynamical Systems
In recent years, there has been a growing interest in the effects of data poisoning attacks on data-driven control methods. Poisoning attacks are well-known to the Machine Learning community, which, however, make use of …
Data PoisoningPoisoning Network Flow Classifiers
As machine learning (ML) classifiers increasingly oversee the automated monitoring of network traffic, studying their resilience against adversarial attacks becomes critical. This paper focuses on poisoning attacks, spec…