{"ID":2855744,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.12468","arxiv_id":"2510.12468","title":"MS-GAGA: Metric-Selective Guided Adversarial Generation Attack","abstract":"We present MS-GAGA (Metric-Selective Guided Adversarial Generation Attack), a two-stage framework for crafting transferable and visually imperceptible adversarial examples against deepfake detectors in black-box settings. In Stage 1, a dual-stream attack module generates adversarial candidates: MNTD-PGD applies enhanced gradient calculations optimized for small perturbation budgets, while SG-PGD focuses perturbations on visually salient regions. This complementary design expands the adversarial search space and improves transferability across unseen models. In Stage 2, a metric-aware selection module evaluates candidates based on both their success against black-box models and their structural similarity (SSIM) to the original image. By jointly optimizing transferability and imperceptibility, MS-GAGA achieves up to 27% higher misclassification rates on unseen detectors compared to state-of-the-art attacks.","short_abstract":"We present MS-GAGA (Metric-Selective Guided Adversarial Generation Attack), a two-stage framework for crafting transferable and visually imperceptible adversarial examples against deepfake detectors in black-box settings. In Stage 1, a dual-stream attack module generates adversarial candidates: MNTD-PGD applies enhance...","url_abs":"https://arxiv.org/abs/2510.12468","url_pdf":"https://arxiv.org/pdf/2510.12468v1","authors":"[\"Dion J. X. Ho\",\"Gabriel Lee Jun Rong\",\"Niharika Shrivastava\",\"Harshavardhan Abichandani\",\"Pai Chet Ng\",\"Xiaoxiao Miao\"]","published":"2025-10-14T13:01:40Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}