In Anticipation of Perfect Deepfake: Identity-anchored Artifact-agnostic Detection under Rebalanced Deepfake Detection Protocol

arXiv:2405.00483v1 Announce Type: new
Abstract: As deep generative models advance, we anticipate deepfakes achieving "perfection"-generating no discernible artifacts or noise. However, current deepfake detectors, intentionally or inadvertently, rely on such artifacts for detection, as they are exclusive to deepfakes and absent in genuine examples. To bridge this gap, we introduce the Rebalanced Deepfake Detection Protocol (RDDP) to stress-test detectors under balanced scenarios where genuine and forged examples bear similar artifacts. We offer two RDDP variants: RDDP-WHITEHAT uses white-hat deepfake algorithms …

abstract advance artifact arxiv bridge cs.cv cs.mm current deepfake deepfake detectors deepfakes deep generative models detection detectors examples exclusive generative generative models however identity noise protocol type