paper-with-me

Papers

Stealthy LLM-Driven Data Poisoning Attacks Against Embedding-Based Retrieval-Augmented Recommender Systems

2025-05-08 · Fatemeh Nazary, Yashar Deldjoo, Tommaso Di Noia, Eugenio Di Sciascio

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.

📄 PDF Abstract BibTeX arXiv:2505.05196

Code (0)

등록된 구현이 없습니다.

Tasks

Data PoisoningLanguage ModelingLanguage ModellingLarge Language ModelRAGRecommendation SystemsRetrievalSemantic SimilaritySemantic Textual Similarity

Similar Papers 제목 키워드 기반

Stealthy Poisoning Attacks Bypass Defenses in Regression Settings

2026-01-29 · Javier Carnerero-Cano, Luis Muñoz-González, Phillippa Spencer, Emil C. Lupu arxiv

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

2024-02-21 · Zhiwei Wang, Huazheng Wang, Hongning Wang

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 Bandits

Subpopulation Data Poisoning Attacks

2020-06-24 · Matthew Jagielski, Giorgio Severi, Niklas Pousette Harger, Alina Oprea

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 Poisoning

Analysis and Detectability of Offline Data Poisoning Attacks on Linear Dynamical Systems

2022-11-16 · Alessio Russo

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 Poisoning

Poisoning Network Flow Classifiers

2023-06-02 · Giorgio Severi, Simona Boboila, Alina Oprea, John Holodnak 외

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…