Salvato in:
Dettagli Bibliografici
Autori principali: Yao, Junyi, Zheng, Zihao, Long, Jiayu
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.17805
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917420865683456
author Yao, Junyi
Zheng, Zihao
Long, Jiayu
author_facet Yao, Junyi
Zheng, Zihao
Long, Jiayu
contents Pairwise ranking systems based on Maximum Likelihood Estimation (MLE), such as the Bradley-Terry model, are widely used to aggregate preferences from pairwise comparisons. However, their robustness under strategic data manipulation remains insufficiently understood. In this paper, we study the vulnerability of MLE-based ranking systems to adversarial perturbations. We formulate the manipulation task as a constrained combinatorial optimization problem and propose an Adaptive Subset Selection Attack (ASSA) to efficiently identify high-impact perturbations. Experimental results on both synthetic data and real-world election datasets show that MLE-based rankings exhibit a sharp phase-transition behavior: beyond a small perturbation budget, a limited number of strategic voters can significantly alter the global ranking. In particular, our method consistently outperforms random and greedy baselines under constrained budgets. These findings reveal a fundamental sensitivity of MLE-based ranking mechanisms to structured perturbations and highlight the need for more robust aggregation methods in collective decision-making systems.
format Preprint
id arxiv_https___arxiv_org_abs_2604_17805
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Ranking Abuse via Strategic Pairwise Data Perturbations
Yao, Junyi
Zheng, Zihao
Long, Jiayu
Machine Learning
Artificial Intelligence
Computer Science and Game Theory
Pairwise ranking systems based on Maximum Likelihood Estimation (MLE), such as the Bradley-Terry model, are widely used to aggregate preferences from pairwise comparisons. However, their robustness under strategic data manipulation remains insufficiently understood. In this paper, we study the vulnerability of MLE-based ranking systems to adversarial perturbations. We formulate the manipulation task as a constrained combinatorial optimization problem and propose an Adaptive Subset Selection Attack (ASSA) to efficiently identify high-impact perturbations. Experimental results on both synthetic data and real-world election datasets show that MLE-based rankings exhibit a sharp phase-transition behavior: beyond a small perturbation budget, a limited number of strategic voters can significantly alter the global ranking. In particular, our method consistently outperforms random and greedy baselines under constrained budgets. These findings reveal a fundamental sensitivity of MLE-based ranking mechanisms to structured perturbations and highlight the need for more robust aggregation methods in collective decision-making systems.
title Ranking Abuse via Strategic Pairwise Data Perturbations
topic Machine Learning
Artificial Intelligence
Computer Science and Game Theory
url https://arxiv.org/abs/2604.17805