MARS is a transfer-based black-box attack that uses bi-level optimization on semantic and artifact anchors to escape the linearity trap and improve attack success rates on SSL-SVDD by up to 36%.
Adversarial attacks on audio deepfake detection: A benchmark and comparative study,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Escaping the Linearity Trap: Manifold Detours for Black-Box Adversarial Attacks on Singing Audio Deepfake Detection
MARS is a transfer-based black-box attack that uses bi-level optimization on semantic and artifact anchors to escape the linearity trap and improve attack success rates on SSL-SVDD by up to 36%.