dorsal/arxiv
View SchemaAl\'em do Desempenho: Um Estudo da Confiabilidade de Detectores de Deepfakes
| Authors | Lucas Lopes, Rayson Laroca, André Grégio |
|---|---|
| Categories | |
| ArXiv ID | 2601.08674vv1 |
| URL | https://arxiv.org/abs/2601.08674 |
| DOI | 10.5753/sbseg.2025.11431 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
Deepfakes are synthetic media generated by artificial intelligence, with positive applications in education and creativity, but also serious negative impacts such as fraud, misinformation, and privacy violations. Although detection techniques have advanced, comprehensive evaluation methods that go beyond classification performance remain lacking. This paper proposes a reliability assessment framework based on four pillars: transferability, robustness, interpretability, and computational efficiency. An analysis of five state-of-the-art methods revealed significant progress as well as critical limitations.
{
"annotation_id": "225431fd-91bf-4110-80fc-a13f2040fd16",
"date_created": "2026-02-17T05:53:15.297000Z",
"date_modified": "2026-02-17T05:53:15.297000Z",
"file_hash": "cab4cd895663a607370543cb7916bc27f442bbdbb2b3bc18523fca42c182fb34",
"private": false,
"record": {
"abstract": "Deepfakes are synthetic media generated by artificial intelligence, with positive applications in education and creativity, but also serious negative impacts such as fraud, misinformation, and privacy violations. Although detection techniques have advanced, comprehensive evaluation methods that go beyond classification performance remain lacking. This paper proposes a reliability assessment framework based on four pillars: transferability, robustness, interpretability, and computational efficiency. An analysis of five state-of-the-art methods revealed significant progress as well as critical limitations.",
"arxiv_id": "2601.08674",
"authors": [
"Lucas Lopes",
"Rayson Laroca",
"Andr\u00e9 Gr\u00e9gio"
],
"categories": [
"cs.CV",
"cs.LG"
],
"doi": "10.5753/sbseg.2025.11431",
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "Al\\\u0027em do Desempenho: Um Estudo da Confiabilidade de Detectores de Deepfakes",
"url": "https://arxiv.org/abs/2601.08674",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "4cae6ea3-21ad-4519-b339-a42660adb11e",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}