PhD Position in Explainable DeepFake Detection Using Foundation Models

This fully funded four-year PhD position at the University of Twente focuses on developing explainable methods for detecting DeepFake manipulations using foundation models. The successful candidate will investigate inconsistencies in video and audio data, leveraging advanced computer vision and AI techniques to enhance detection accuracy and interpretability. The project aligns with growing concerns about digital media authenticity and aims to contribute novel solutions to this critical challenge. Applicants should have a strong background in computer science or electrical engineering, with expertise in AI and computer vision. The position offers a collaborative research environment and the opportunity to work at the intersection of AI, security, and multimedia analysis.

• Develop and implement explainable AI models to detect inconsistencies in video and audio data related to DeepFake manipulations.
• Conduct research on the application of foundation models in multimedia forensics and their interpretability.
• Analyze and evaluate the performance of detection algorithms on various types of multimedia data.
• Collaborate with interdisciplinary teams to integrate findings into broader AI security frameworks.
• Present research findings at international conferences and publish results in top-tier academic journals.
• Contribute to the development of novel methodologies for enhancing the robustness and transparency of AI-driven detection systems.