Join Scale AI at their San Francisco Headquarters for their monthly ML & AI Meetup. This event will bring together a group of practitioners and engineers within the AI & ML communities for an in-person Tech Talk, followed by the opportunity to network and exchange ideas on continued advancements and the future of AI. The event is free to attend. Drinks and a light meal will be provided.
State-of-the-art (SOTA) Generative Models (GMs) can synthesize photo-realistic images that are hard for humans to distinguish from genuine photos. Identifying and understanding manipulated media are crucial to mitigate the social concerns on the potential misuse of GMs. We propose to perform reverse engineering of GMs to infer model hyperparameters from the images generated by these models. We define a novel problem, "model parsing", as estimating GM network architectures and training loss functions by examining their generated images - a task seemingly impossible for human beings. To tackle this problem, we propose a framework with two components: a Fingerprint Estimation Network (FEN), which estimates a GM fingerprint from a generated image by training with four constraints to encourage the fingerprint to have desired properties, and a Parsing Network (PN), which predicts network architecture and loss functions from the estimated fingerprints. To evaluate our approach, we collect a fake image dataset with 100K images generated by 116 different GMs. Extensive experiments show encouraging results in parsing the hyperparameters of the unseen models. Finally, our fingerprint estimation can be leveraged for deepfake detection and image attribution, as we show by reporting SOTA results on both the deepfake detection (Celeb-DF) and image attribution benchmarks.
To attend the event, please RSVP via this registration page.
To gain access to the building, all attendees must sign-in upon arrival, sign an NDA, and provide proof of full vaccination and booster status or negative antigen test.