Cloned Voices, Real Consequences: Evaluating Bias in Political Deepfake Detection for Electoral Integrity in Brazil
克隆语音,真实后果:评估巴西选举诚信相关的政治深度伪造检测中的偏差
Lucas Rafael Stefanel Gris, Daniel Casanova, Frederico Santos De Oliveira, Alef Iury Ferreira, Beatriz Almeida Felício, Raul César Reis Mata, Anderson da Silva Soares
Comments9 pages, 2 propositions, 2 tables. Major pre-publication correction: the archived sample is a 2.285-day legacy-CTF-only block range, not a seven-day venue sample. The revision makes record-level two-sided attribution and mint/burn direction limits explicit and narrows clustering and concentration claims. No new empirical run
机构
*
Independent Researcher(独立研究者)
;
Hunan University(湖南大学)
;
Shenzhen Kaihong Digital Industry Development Co., Ltd.(深圳凯鸿数字产业开发有限公司)
;
Central University of Finance and Economics(中央财经大学)
;
Chongqing University(重庆大学)
;
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
;
Stevens Institute of Technology(斯蒂文斯理工学院)
;
Cornell University(康奈尔大学)
;
Oak Ridge National Laboratory(橡树岭国家实验室)
;
Zhengzhou University of Light Industry(郑州轻工业大学)
;
Xidian University(西安电子科技大学)
;
The University of Texas at Dallas(德克萨斯大学达拉斯分校)
;
AI Safety Research Lab, Institute of Advanced Computing(高级计算研究所人工智能安全研究实验室)
;
University of Malaya(马来亚大学)
;
Emory University(埃默里大学)
;
Department of Nephrology, Affiliated Hospital of Guangdong Medical University(广东医学院附属医院肾内科)
CommentsAccepted to the AI-SS 2026 Workshop at the 21st European Dependable Computing Conference (EDCC 2026). To be published in the EDCC Companion Proceedings (EDCC-C)