Recommender Systems for Democracy: Toward Adversarial Robustness in Voting Advice Applications

TL;DR

This paper investigates vulnerabilities in voting advice applications (VAAs), exposing manipulation strategies, measuring their impact, and proposing robustness metrics to enhance their security and reliability in democratic processes.

Contribution

It identifies specific manipulation tactics in VAAs, quantifies their effects, and introduces empirical metrics and robustness properties to improve VAA security against adversarial attacks.

Findings

Manipulation can alter party recommendations by over 261%.

Adjusting matching methods can shift recommendation frequencies by up to 105%.

Proposed metrics help assess and improve VAA robustness.

Abstract

Voting advice applications (VAAs) help millions of voters understand which political parties or candidates best align with their views. This paper explores the potential risks these applications pose to the democratic process when targeted by adversarial entities. In particular, we expose 11 manipulation strategies and measure their impact using data from Switzerland's primary VAA, Smartvote, collected during the last two national elections. We find that altering application parameters, such as the matching method, can shift a party's recommendation frequency by up to 105%. Cherry-picking questionnaire items can increase party recommendation frequency by over 261%, while subtle changes to parties' or candidates' responses can lead to a 248% increase. To address these vulnerabilities, we propose adversarial robustness properties VAAs should satisfy, introduce empirical metrics for assessing the resilience of various matching methods, and suggest possible avenues for research toward mitigating the effect of manipulation. Our framework is key to ensuring secure and reliable AI-based VAAs poised to emerge in the near future.