Search Results for author: Shengbang Fang

Found 4 papers, 0 papers with code

Open Set Synthetic Image Source Attribution

no code implementations22 Aug 2023 Shengbang Fang, Tai D. Nguyen, Matthew C. Stamm

To address this new threat, researchers have developed multiple algorithms to detect synthetic images and identify their source generators.

Attribute Image Generation +2

VideoFACT: Detecting Video Forgeries Using Attention, Scene Context, and Forensic Traces

no code implementations28 Nov 2022 Tai D. Nguyen, Shengbang Fang, Matthew C. Stamm

While existing forensic networks have demonstrated strong performance on image forgeries, recent results reported on the Adobe VideoSham dataset show that these networks fail to identify fake content in videos.

Misinformation

Attacking Image Splicing Detection and Localization Algorithms Using Synthetic Traces

no code implementations22 Nov 2022 Shengbang Fang, Matthew C Stamm

Through a series of experiments, we demonstrate that our attack is capable of fooling forensic splicing detection and localization algorithms without introducing visually detectable artifacts into an attacked image.

Generative Adversarial Network

Cannot find the paper you are looking for? You can Submit a new open access paper.