deepfake detectors
PulseAugur coverage of deepfake detectors — every cluster mentioning deepfake detectors across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New ISPCloak method uses physical camouflage to evade deepfake detectors
Researchers have developed a new method called ISPCloak that weaponizes the Image Signal Processing (ISP) pipeline to create physical camouflage for AI-generated images, making them undetectable by deepfake detectors. T…
-
New Calibrated Deepfake Trust Score Links Detector Competence to Trustworthiness
Researchers have developed a new metric called the Calibrated Deepfake Trust Score (CDTS) to better assess the trustworthiness of deepfake detection systems. The CDTS highlights a critical relationship: as a detector's …
-
New Cross-AUC metric offers realistic evaluation for deepfake detectors
Researchers have introduced a new metric called Cross-AUC to better evaluate the performance of deepfake detectors. Traditional methods using Area Under the ROC Curve (AUC) can be misleading when detectors encounter dat…
-
Language models enhance deepfake detector generalization and interpretability
Researchers have developed a novel method for training deepfake detectors by leveraging multimodal large language models (MLLMs). This approach uses language as a regularization mechanism to improve both the generalizab…