Metraipolis › archive › dc_4aeb3426fa9a
Black-Box Adversarial Example Attacks on Machine Learning based Election Systems — arXiv:2611.02166
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02166
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:19:44.020Z
- SHA-256 of the archived text
d22de0e9ff8254e8404010ea08549cdea4db2cd465695df91c56dd8c0be38865- Stable URL of this page
https://metraipolis.com/documento/dc_4aeb3426fa9a
How to cite
Black-Box Adversarial Example Attacks on Machine Learning based Election Systems — arXiv:2611.02166 — arXiv (en), https://arxiv.org/abs/2611.02166 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4aeb3426fa9a (Metraipolis archive dc_4aeb3426fa9a, sha256 d22de0e9ff8254e8404010ea08549cdea4db2cd465695df91c56dd8c0be38865)
BibTeX
@misc{dc4aeb3426fa9a,
title = {Black-Box Adversarial Example Attacks on Machine Learning based Election Systems — arXiv:2611.02166},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02166},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4aeb3426fa9a; sha256 d22de0e9ff8254e8404010ea08549cdea4db2cd465695df91c56dd8c0be38865},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02166. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Machine learning models have shown exceptional accuracy for ballot classification in election systems. Recent research has demonstrated that these ballot classification models are vulnerable to adversarial example attacks. This is a critical security issue because a successful attack could alter the outcome of an election and undermine the democratic process. However, all adversarial example attacks in the voting domain have assumed a white-box threat model, where the classifier parameters are known. In this work, we advance the field of machine learning in election systems by analyzing a realistic black-box adversary. We implement and evaluate eleven state-of-the-art black-box attacks: query based attacks ADBA, Square, SurFree, RayS, and SA-MOO. We also test adaptive transfer based black-box attacks with APGD-$l_\infty$, APGD-$l_2$, APGD-$l_1$, PGD $l_0$, PGD $l_0$+$l_\infty$, and PGD $l_0$+$\sigma$. Our attacks span multiple different norms ($l_\infty$, $l_2$, $l_1$, and $l_0$) and three different black-box adversarial threat models (decision based, score based and transfer based). In addition to digital analyses, we physically print and scan $20,000$ adversarial examples to evaluate the real-world performance of different black-box attacks. Our finding demonstrate an even larger physical-digital robustness gap exists for black-box adversarial examples than for white-box adversarial examples. Lastly, we conduct the first ever adversarial example transferability study in the voting domain and test adversarial training and barrier zones as two possible black-box defense strategies. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.02166 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T18:09:53.662Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).