AIBearisharXiv – CS AI · Mar 127/10
🧠
Na\"ive Exposure of Generative AI Capabilities Undermines Deepfake Detection
Researchers demonstrate that commercial AI chatbot interfaces inadvertently expose capabilities that allow adversaries to bypass deepfake detection systems using only policy-compliant prompts. The study reveals that current deepfake detectors fail against semantic-preserving image refinement techniques enabled by widely accessible AI systems.