Yichao Zhou

Nanjing University of Science and Technology

Papers

Total Citations

H-Index

About

Yichao Zhou is a rising researcher at the forefront of artificial intelligence safety, specializing in deepfake detection and embodied AI security. His most-cited work, "A new deepfake detection model for responding to perception attacks in embodied artificial intelligence" (2024), addresses a critical vulnerability in AI systems that interact with the physical world—perception attacks that can deceive autonomous agents into misinterpreting their environment. By developing a robust detection framework, Zhou’s research helps safeguard embodied AI applications, from autonomous vehicles to robotic assistants, against malicious visual manipulations. With 10 citations in just its first year, this paper signals growing recognition of his contributions to AI trustworthiness. Zhou’s work bridges computer vision, adversarial machine learning, and cybersecurity, offering practical defenses against emerging threats. His achievements highlight a commitment to making AI not only more capable but also more resilient, positioning him as a key voice in the next generation of AI safety researchers. For students and researchers, Zhou’s research underscores the urgent need to anticipate and counter perception-based attacks as AI becomes increasingly integrated into daily life.