Hugging Face Trending Papers
Scalable Black-Box Model Attribution for Images
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Computer Vision
Sep 22
Scalable Black-Box Model Attribution for Images
arXiv:2608.15652v2 Announce Type: replace Abstract: The rapid proliferation of generative models raises the model attribution problem: given only an image, can we determine which model produced it? W...
arXiv Machine Learning
Jun 30
$\mu$Flow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors
arXiv:2606. 30528v1 Announce Type: cross Abstract: Current generative models, including GANs and diffusion models, have reached an outstanding level of photorealism, posing significant risks to privacy and security.
arXiv AI
Jun 12
Proto-LeakNet: Towards Signal-Leak Aware Attribution in Synthetic Human Face Imagery
arXiv:2511. 04260v3 Announce Type: replace-cross Abstract: The growing sophistication of synthetic image and deepfake generation models has turned source attribution and authenticity verification into a critical challenge for modern computer vision systems.
arXiv Computer Vision
Sep 15
Learning Continuous Source Responses For Generalizable AI-Generated Image Detection
arXiv:2609.14316v1 Announce Type: new Abstract: Advances in image generation have made synthetic images increasingly difficult to distinguish from real photographs, raising concerns about the trustwo...
arXiv AI
Oct 12
Hide and Seek: HIDE Concepts to SEEK explanations for black box models
Hide and Seek (HnS) is a concept‑level attribution method that interprets black‑box vision models without needing model weights or labeled concept datasets. It retrieves concept‑aligned images via a vision‑language model, localizes and masks the concept region, and measures attribution by observing changes in the model’s output. HnS was validated on CelebA and COCO‑Stuff, showing stronger agreement with ground‑truth attributions than existing methods, and was applied to tasks like image captioning and satellite image segmentation where other concept attribution methods fail.
arXiv AI
Jun 24
MGI: Member vs Generated Inference
arXiv:2606. 23872v1 Announce Type: cross Abstract: As generative models increasingly produce samples that are indistinguishable from human-created content, it becomes difficult to determine whether a given data point was part of a model's natural training set or was generated by the model itself, especially when models memorize and reproduce training data.