5 papers
Can Pixels Alone Reveal Image Origin? Minimax Limits and Learnable Interfaces for Passive Provenance
Kai Yao
Passive image provenance asks whether pixels alone can reveal where an image came from: a human, an aggregate AI class, or a particular generator. This becomes a robustness problem…
FARE: Forensic Acceptance Region Estimation for Catching Bait-and-Switch Image Generators
Kai Yao, Marc Juarez
Modern AI image generators are increasingly deployed as opaque APIs, where customers can query the deployed service, but cannot inspect model weights or architecture. This creates…
Smudged Fingerprints: A Systematic Evaluation of the Robustness of AI Image Fingerprints
Kai Yao, Marc Juarez
Model fingerprint detection has shown promise to trace the provenance of AI-generated images in forensic applications. However, despite the inherent adversarial nature of these app…
SPRINT: Robust Model Attribution of Generated Images via Secret Pixel Reconstruction
Kai Yao, Marc Juarez
Detecting the source model of AI-generated images is a growing accountability problem. AI fingerprinting techniques address this by detecting imperceptible patterns in the images t…
SoK: What Makes Private Learning Unfair?
Kai Yao, Marc Juarez
Differential privacy has emerged as the most studied framework for privacy-preserving machine learning. However, recent studies show that enforcing differential privacy guarantees…