Cristi Isaula-Reyes
Research Mentor(s): Renee Li
Mentor Department: UMSI
Authors: Qiwei Li
Session: Session 7 (4:00pm – 4: 50pm)
Presentation Type: Oral
Abstract
The advancement of artificial intelligence, including deepfake technology, has significantly contributed to the spread of non-consensual intimate media (NCIM), leaving victims with limited and inefficient means of detection and reporting their intimate content being distributed without consent. The difficulty of reporting NCIM varies depending on how widely an image is disseminated and the complexity of the reporting process on each platform; however, all current methods require victims to manually locate and report harmful content, a process that is both emotionally distressing and logistically challenging for victims. Our proposed system uses reverse image searching coupled with automated web browsing agents to detect instances of NCIM and automatically report them. By eliminating the burden of manual reporting, we aim to mitigate the psychological toll on victims while enhancing the effectiveness of NCIM detection. Our work highlights the potential of AI-driven solutions to address the growing misuse of generative technologies. Future developments will focus on improving system accuracy, ensuring ethical deployment, and refining mechanisms for seamless integration with existing enforcement efforts. Through this research, we contribute to the foundation of scalable, victim-centered approaches for combating the distribution of NCIM.
